Authors: Juexiao Zhou, Zhongyi Han, Mankun Xin, Xingwei He, Guotao Wang, Jiaoyan Song, Gongning Luo, Wenjia He, Xintong Li, Yuetan Chu, Juanwen Chen, Bo Wang, Xia Wu, Wenwen Duan, Zhixia Guo, Liyan Bai, Yilin Pan, Xuefei Bi, Lu Liu, Long Feng, Xiaonan He, Xin Gao
Abstract: Global population aging presents increasing challenges to healthcare systems, with coronary artery disease (CAD) responsible for approximately 17.8 million deaths annually, making it a leading cause of global mortality. As CAD is largely preventable, early detection and proactive management are essential. In this work, we introduce DigitalShadow, an advanced early warning system for CAD, powered by a fine-tuned facial foundation model. The system is pre-trained on 21 million facial images and subsequently fine-tuned into LiveCAD, a specialized CAD risk assessment model trained on 7,004 facial images from 1,751 subjects across four hospitals in China. DigitalShadow functions passively and contactlessly, extracting facial features from live video streams without requiring active user engagement. Integrated with a personalized database, it generates natural language risk reports and individualized health recommendations. With privacy as a core design principle, DigitalShadow supports local deployment to ensure secure handling of user data.
Authors: Rifat Sadik, Tanvir Rahman, Arpan Bhattacharjee, Bikash Chandra Halder, Ismail Hossain
Abstract: Deep learning models have shown remarkable success in dermatological image analysis, offering potential for automated skin disease diagnosis. Previously, convolutional neural network(CNN) based architectures have achieved immense popularity and success in computer vision (CV) based task like skin image recognition, generation and video analysis. But with the emergence of transformer based models, CV tasks are now are nowadays carrying out using these models. Vision Transformers (ViTs) is such a transformer-based models that have shown success in computer vision. It uses self-attention mechanisms to achieve state-of-the-art performance across various tasks. However, their reliance on global attention mechanisms makes them susceptible to adversarial perturbations. This paper aims to investigate the susceptibility of ViTs for medical images to adversarial watermarking-a method that adds so-called imperceptible perturbations in order to fool models. By generating adversarial watermarks through Projected Gradient Descent (PGD), we examine the transferability of such attacks to CNNs and analyze the performance defense mechanism -- adversarial training. Results indicate that while performance is not compromised for clean images, ViTs certainly become much more vulnerable to adversarial attacks: an accuracy drop of as low as 27.6%. Nevertheless, adversarial training raises it up to 90.0%.
Authors: A. Postlmayr, P. Cosman, S. Dey
Abstract: We introduce a fitness tracking system that enables remote monitoring for exercises using only a RGB smartphone camera, making fitness tracking more private, scalable, and cost effective. Although prior work explored automated exercise supervision, existing models are either too limited in exercise variety or too complex for real-world deployment. Prior approaches typically focus on a small set of exercises and fail to generalize across diverse movements. In contrast, we develop a robust, multitask motion analysis model capable of performing exercise detection and repetition counting across hundreds of exercises, a scale far beyond previous methods. We overcome previous data limitations by assembling a large-scale fitness dataset, Olympia covering more than 1,900 exercises. To our knowledge, our vision-language model is the first that can perform multiple tasks on skeletal fitness data. On Olympia, our model can detect exercises with 76.5% accuracy and count repetitions with 85.3% off-by-one accuracy, using only RGB video. By presenting a single vision-language transformer model for both exercise identification and rep counting, we take a significant step toward democratizing AI-powered fitness tracking.
Authors: Mingqi Jiang, Chanho Kim, Chen Ziwen, Li Fuxin
Abstract: Traditional SLAM algorithms are excellent at camera tracking but might generate lower resolution and incomplete 3D maps. Recently, Gaussian Splatting (GS) approaches have emerged as an option for SLAM with accurate, dense 3D map building. However, existing GS-based SLAM methods rely on per-scene optimization which is time-consuming and does not generalize to diverse scenes well. In this work, we introduce the first generalizable GS-based semantic SLAM algorithm that incrementally builds and updates a 3D scene representation from an RGB-D video stream using a learned generalizable network. Our approach starts from an RGB-D image recognition backbone to predict the Gaussian parameters from every downsampled and backprojected image location. Additionally, we seamlessly integrate 3D semantic segmentation into our GS framework, bridging 3D mapping and recognition through a shared backbone. To correct localization drifting and floaters, we propose to optimize the GS for only 1 iteration following global localization. We demonstrate state-of-the-art semantic SLAM performance on the real-world benchmark ScanNet with an order of magnitude fewer Gaussians compared to other recent GS-based methods, and showcase our model's generalization capability through zero-shot transfer to the NYUv2 and TUM RGB-D datasets.
Authors: Seung-jae Lee, Paul Hongsuck Seo
Abstract: Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on large-scale pixel-level annotations, which are costly and time-consuming to obtain. To address this, we propose a novel zero-shot AVS framework that eliminates task-specific training by leveraging multiple pretrained models. Our approach integrates audio, vision, and text representations to bridge modality gaps, enabling precise sound source segmentation without AVS-specific annotations. We systematically explore different strategies for connecting pretrained models and evaluate their efficacy across multiple datasets. Experimental results demonstrate that our framework achieves state-of-the-art zero-shot AVS performance, highlighting the effectiveness of multimodal model integration for finegrained audiovisual segmentation.
Authors: Thushari Hapuarachchi, Long Dang, Kaiqi Xiong
Abstract: Deep Neural Networks (DNNs) are widely used for traffic sign recognition because they can automatically extract high-level features from images. These DNNs are trained on large-scale datasets obtained from unknown sources. Therefore, it is important to ensure that the models remain secure and are not compromised or poisoned during training. In this paper, we investigate the robustness of DNNs trained for traffic sign recognition. First, we perform the error-minimizing attacks on DNNs used for traffic sign recognition by adding imperceptible perturbations on training data. Then, we propose a data augmentation-based training method to mitigate the error-minimizing attacks. The proposed training method utilizes nonlinear transformations to disrupt the perturbations and improve the model robustness. We experiment with two well-known traffic sign datasets to demonstrate the severity of the attack and the effectiveness of our mitigation scheme. The error-minimizing attacks reduce the prediction accuracy of the DNNs from 99.90% to 10.6%. However, our mitigation scheme successfully restores the prediction accuracy to 96.05%. Moreover, our approach outperforms adversarial training in mitigating the error-minimizing attacks. Furthermore, we propose a detection model capable of identifying poisoned data even when the perturbations are imperceptible to human inspection. Our detection model achieves a success rate of over 99% in identifying the attack. This research highlights the need to employ advanced training methods for DNNs in traffic sign recognition systems to mitigate the effects of data poisoning attacks.
Authors: Yannis Spyridis, Vasileios Argyriou
Abstract: Automated sorting is crucial for improving the efficiency and scalability of textile recycling, but accurately identifying material composition and detecting contaminants from sensor data remains challenging. This paper investigates the use of standard RGB imagery, a cost-effective sensing modality, for key pre-processing tasks in an automated system. We present computer vision components designed for a conveyor belt setup to perform (a) classification of four common textile types and (b) segmentation of non-textile features such as buttons and zippers. For classification, several pre-trained architectures were evaluated using transfer learning and cross-validation, with EfficientNetB0 achieving the best performance on a held-out test set with 81.25\% accuracy. For feature segmentation, a zero-shot approach combining the Grounding DINO open-vocabulary detector with the Segment Anything Model (SAM) was employed, demonstrating excellent performance with a mIoU of 0.90 for the generated masks against ground truth. This study demonstrates the feasibility of using RGB images coupled with modern deep learning techniques, including transfer learning for classification and foundation models for zero-shot segmentation, to enable essential analysis steps for automated textile recycling pipelines.
Authors: Anees Nashath Shaik, Barbara Villarini, Vasileios Argyriou
Abstract: Surveillance systems play a critical role in security and reconnaissance, but their performance is often compromised by low-quality images and videos, leading to reduced accuracy in face recognition. Additionally, existing AI-based facial analysis models suffer from biases related to skin tone variations and partially occluded faces, further limiting their effectiveness in diverse real-world scenarios. These challenges are the results of data limitations and imbalances, where available training datasets lack sufficient diversity, resulting in unfair and unreliable facial recognition performance. To address these issues, we propose a data-driven platform that enhances surveillance capabilities by generating synthetic training data tailored to compensate for dataset biases. Our approach leverages deep learning-based facial attribute manipulation and reconstruction using autoencoders and Generative Adversarial Networks (GANs) to create diverse and high-quality facial datasets. Additionally, our system integrates an image enhancement module, improving the clarity of low-resolution or occluded faces in surveillance footage. We evaluate our approach using the CelebA dataset, demonstrating that the proposed platform enhances both training data diversity and model fairness. This work contributes to reducing bias in AI-based facial analysis and improving surveillance accuracy in challenging environments, leading to fairer and more reliable security applications.
Authors: Youssef Farah, Federico Paredes-Vall\'es, Guido De Croon, Muhammad Ahmed Humais, Hussain Sajwani, Yahya Zweiri
Abstract: Event cameras are novel bio-inspired sensors that capture motion dynamics with much higher temporal resolution than traditional cameras, since pixels react asynchronously to brightness changes. They are therefore better suited for tasks involving motion such as motion segmentation. However, training event-based networks still represents a difficult challenge, as obtaining ground truth is very expensive, error-prone and limited in frequency. In this article, we introduce EV-LayerSegNet, a self-supervised CNN for event-based motion segmentation. Inspired by a layered representation of the scene dynamics, we show that it is possible to learn affine optical flow and segmentation masks separately, and use them to deblur the input events. The deblurring quality is then measured and used as self-supervised learning loss. We train and test the network on a simulated dataset with only affine motion, achieving IoU and detection rate up to 71% and 87% respectively.
Authors: Tan-Hanh Pham, Chris Ngo
Abstract: The growing integration of vision-language models (VLMs) in medical applications offers promising support for diagnostic reasoning. However, current medical VLMs often face limitations in generalization, transparency, and computational efficiency-barriers that hinder deployment in real-world, resource-constrained settings. To address these challenges, we propose a Reasoning-Aware Reinforcement Learning framework, \textbf{RARL}, that enhances the reasoning capabilities of medical VLMs while remaining efficient and adaptable to low-resource environments. Our approach fine-tunes a lightweight base model, Qwen2-VL-2B-Instruct, using Low-Rank Adaptation and custom reward functions that jointly consider diagnostic accuracy and reasoning quality. Training is performed on a single NVIDIA A100-PCIE-40GB GPU, demonstrating the feasibility of deploying such models in constrained environments. We evaluate the model using an LLM-as-judge framework that scores both correctness and explanation quality. Experimental results show that RARL significantly improves VLM performance in medical image analysis and clinical reasoning, outperforming supervised fine-tuning on reasoning-focused tasks by approximately 7.78%, while requiring fewer computational resources. Additionally, we demonstrate the generalization capabilities of our approach on unseen datasets, achieving around 27% improved performance compared to supervised fine-tuning and about 4% over traditional RL fine-tuning. Our experiments also illustrate that diversity prompting during training and reasoning prompting during inference are crucial for enhancing VLM performance. Our findings highlight the potential of reasoning-guided learning and reasoning prompting to steer medical VLMs toward more transparent, accurate, and resource-efficient clinical decision-making. Code and data are publicly available.
Authors: Santhosh Kakarla, Gautama Shastry Bulusu Venkata
Abstract: Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25\% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6\% (shirt), 40.1\% (dress), and 50.4\% (top-tee) and increasing the average Recall@50 to 67.6\%. We also examine Retrieval-DPO, which fine-tunes CLIP's text encoder with a Direct Preference Optimization loss applied to FAISS-mined hard negatives. Despite extensive tuning of the scaling factor, index, and sampling strategy, Retrieval-DPO attains only 0.02\% Recall@10 -- far below zero-shot and prompt-tuned baselines -- because it (i) lacks joint image-text fusion, (ii) uses a margin objective misaligned with top-$K$ metrics, (iii) relies on low-quality negatives, and (iv) keeps the vision and Transformer layers frozen. Our results show that effective preference-based CIR requires genuine multimodal fusion, ranking-aware objectives, and carefully curated negatives.
Authors: Minghao Zou, Qingtian Zeng, Yongping Miao, Shangkun Liu, Zilong Wang, Hantao Liu, Wei Zhou
Abstract: Visual parsing of images and videos is critical for a wide range of real-world applications. However, progress in this field is constrained by limitations of existing datasets: (1) insufficient annotation granularity, which impedes fine-grained scene understanding and high-level reasoning; (2) limited coverage of domains, particularly a lack of datasets tailored for educational scenarios; and (3) lack of explicit procedural guidance, with minimal logical rules and insufficient representation of structured task process. To address these gaps, we introduce PhysLab, the first video dataset that captures students conducting complex physics experiments. The dataset includes four representative experiments that feature diverse scientific instruments and rich human-object interaction (HOI) patterns. PhysLab comprises 620 long-form videos and provides multilevel annotations that support a variety of vision tasks, including action recognition, object detection, HOI analysis, etc. We establish strong baselines and perform extensive evaluations to highlight key challenges in the parsing of procedural educational videos. We expect PhysLab to serve as a valuable resource for advancing fine-grained visual parsing, facilitating intelligent classroom systems, and fostering closer integration between computer vision and educational technologies. The dataset and the evaluation toolkit are publicly available at https://github.com/ZMH-SDUST/PhysLab.
Authors: Moushumi Medhi, Rajiv Ranjan Sahay
Abstract: In this paper, we utilize the dark channel as a complementary cue to estimate the depth of a scene from a single space-variant defocus blurred image due to its effectiveness in implicitly capturing the local statistics of blurred images and the scene structure. Existing depth-from-defocus (DFD) techniques typically rely on multiple images with varying apertures or focus settings to recover depth information. Very few attempts have focused on DFD from a single defocused image due to the underconstrained nature of the problem. Our method capitalizes on the relationship between local defocus blur and contrast variations as key depth cues to enhance the overall performance in estimating the scene's structure. The entire pipeline is trained adversarially in a fully end-to-end fashion. Experiments conducted on real data with realistic depth-induced defocus blur demonstrate that incorporating dark channel prior into single image DFD yields meaningful depth estimation results, validating the effectiveness of our approach.
Authors: Cheng Peng, Jingxiang Sun, Yushuo Chen, Zhaoqi Su, Zhuo Su, Yebin Liu
Abstract: Photorealistic and animatable human avatars are a key enabler for virtual/augmented reality, telepresence, and digital entertainment. While recent advances in 3D Gaussian Splatting (3DGS) have greatly improved rendering quality and efficiency, existing methods still face fundamental challenges, including time-consuming per-subject optimization and poor generalization under sparse monocular inputs. In this work, we present the Parametric Gaussian Human Model (PGHM), a generalizable and efficient framework that integrates human priors into 3DGS for fast and high-fidelity avatar reconstruction from monocular videos. PGHM introduces two core components: (1) a UV-aligned latent identity map that compactly encodes subject-specific geometry and appearance into a learnable feature tensor; and (2) a disentangled Multi-Head U-Net that predicts Gaussian attributes by decomposing static, pose-dependent, and view-dependent components via conditioned decoders. This design enables robust rendering quality under challenging poses and viewpoints, while allowing efficient subject adaptation without requiring multi-view capture or long optimization time. Experiments show that PGHM is significantly more efficient than optimization-from-scratch methods, requiring only approximately 20 minutes per subject to produce avatars with comparable visual quality, thereby demonstrating its practical applicability for real-world monocular avatar creation.
Authors: Yu-Hsuan Ho, Ali Mostafavi
Abstract: Most post-disaster damage classifiers succeed only when destructive forces leave clear spectral or structural signatures -- conditions rarely present after inundation. Consequently, existing models perform poorly at identifying flood-related building damages. The model presented in this study, Flood-DamageSense, addresses this gap as the first deep-learning framework purpose-built for building-level flood-damage assessment. The architecture fuses pre- and post-event SAR/InSAR scenes with very-high-resolution optical basemaps and an inherent flood-risk layer that encodes long-term exposure probabilities, guiding the network toward plausibly affected structures even when compositional change is minimal. A multimodal Mamba backbone with a semi-Siamese encoder and task-specific decoders jointly predicts (1) graded building-damage states, (2) floodwater extent, and (3) building footprints. Training and evaluation on Hurricane Harvey (2017) imagery from Harris County, Texas -- supported by insurance-derived property-damage extents -- show a mean F1 improvement of up to 19 percentage points over state-of-the-art baselines, with the largest gains in the frequently misclassified "minor" and "moderate" damage categories. Ablation studies identify the inherent-risk feature as the single most significant contributor to this performance boost. An end-to-end post-processing pipeline converts pixel-level outputs to actionable, building-scale damage maps within minutes of image acquisition. By combining risk-aware modeling with SAR's all-weather capability, Flood-DamageSense delivers faster, finer-grained, and more reliable flood-damage intelligence to support post-disaster decision-making and resource allocation.
Authors: Radha Kodali, Venkata Rao Dhulipalla, Venkata Siva Kishor Tatavarty, Madhavi Nadakuditi, Bharadwaj Thiruveedhula, Suryanarayana Gunnam, Durga Prasad Bavirisetti
Abstract: Infertility has a considerable impact on individuals' quality of life, affecting them socially and psychologically, with projections indicating a rise in the upcoming years. In vitro fertilization (IVF) emerges as one of the primary techniques within economically developed nations, employed to address the rising problem of low fertility. Expert embryologists conventionally grade embryos by reviewing blastocyst images to select the most optimal for transfer, yet this process is time-consuming and lacks efficiency. Blastocyst images provide a valuable resource for assessing embryo viability. In this study, we introduce an explainable artificial intelligence (XAI) framework for classifying embryos, employing a fusion of convolutional neural network (CNN) and long short-term memory (LSTM) architecture, referred to as CNN-LSTM. Utilizing deep learning, our model achieves high accuracy in embryo classification while maintaining interpretability through XAI.
Authors: Qianqian Zhao, Chunle Guo, Tianyi Zhang, Junpei Zhang, Peiyang Jia, Tan Su, Wenjie Jiang, Chongyi Li
Abstract: Omnidirectional image and video super-resolution is a crucial research topic in low-level vision, playing an essential role in virtual reality and augmented reality applications. Its goal is to reconstruct high-resolution images or video frames from low-resolution inputs, thereby enhancing detail preservation and enabling more accurate scene analysis and interpretation. In recent years, numerous innovative and effective approaches have been proposed, predominantly based on deep learning techniques, involving diverse network architectures, loss functions, projection strategies, and training datasets. This paper presents a systematic review of recent progress in omnidirectional image and video super-resolution, focusing on deep learning-based methods. Given that existing datasets predominantly rely on synthetic degradation and fall short in capturing real-world distortions, we introduce a new dataset, 360Insta, that comprises authentically degraded omnidirectional images and videos collected under diverse conditions, including varying lighting, motion, and exposure settings. This dataset addresses a critical gap in current omnidirectional benchmarks and enables more robust evaluation of the generalization capabilities of omnidirectional super-resolution methods. We conduct comprehensive qualitative and quantitative evaluations of existing methods on both public datasets and our proposed dataset. Furthermore, we provide a systematic overview of the current status of research and discuss promising directions for future exploration. All datasets, methods, and evaluation metrics introduced in this work are publicly available and will be regularly updated. Project page: https://github.com/nqian1/Survey-on-ODISR-and-ODVSR.
Authors: Saiyu Hu, Chunlei He, Jianfeng Zhang, Dexing Kong, Shoujun Huang
Abstract: Parabolic mean curvature flow-driven active contour models (PMCF-ACMs) are widely used in image segmentation, which however depend heavily on the selection of initial curve configurations. In this paper, we firstly propose several hyperbolic mean curvature flow-driven ACMs (HMCF-ACMs), which introduce tunable initial velocity fields, enabling adaptive optimization for diverse segmentation scenarios. We shall prove that HMCF-ACMs are indeed normal flows and establish the numerical equivalence between dissipative HMCF formulations and certain wave equations using the level set method with signed distance function. Building on this framework, we furthermore develop hyperbolic dual-mode regularized flow-driven ACMs (HDRF-ACMs), which utilize smooth Heaviside functions for edge-aware force modulation to suppress over-diffusion near weak boundaries. Then, we optimize a weighted fourth-order Runge-Kutta algorithm with nine-point stencil spatial discretization when solving the above-mentioned wave equations. Experiments show that both HMCF-ACMs and HDRF-ACMs could achieve more precise segmentations with superior noise resistance and numerical stability due to task-adaptive configurations of initial velocities and initial contours.
Authors: Mufhumudzi Muthivhi, Jiahao Huo, Fredrik Gustafsson, Terence L. van Zyl
Abstract: Mitigating human-wildlife conflict seeks to resolve unwanted encounters between these parties. Computer Vision provides a solution to identifying individuals that might escalate into conflict, such as members of the Big Five African animals. However, environments often contain several varied species. The current state-of-the-art animal classification models are trained under a closed-world assumption. They almost always remain overconfident in their predictions even when presented with unknown classes. This study investigates out-of-distribution (OOD) detection of wildlife, specifically the Big Five. To this end, we select a parametric Nearest Class Mean (NCM) and a non-parametric contrastive learning approach as baselines to take advantage of pretrained and projected features from popular classification encoders. Moreover, we compare our baselines to various common OOD methods in the literature. The results show feature-based methods reflect stronger generalisation capability across varying classification thresholds. Specifically, NCM with ImageNet pre-trained features achieves a 2%, 4% and 22% improvement on AUPR-IN, AUPR-OUT and AUTC over the best OOD methods, respectively. The code can be found here https://github.com/pxpana/BIG5OOD
Authors: Zixian Gao, Chao Yang, Zhanhui Zhou, Xing Xu, Chaochao Lu
Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit hallucination phenomena, where the outputs appear plausible but do not align with the content of the images. To mitigate this issue, we introduce Local Perception Search (LPS), a decoding method during inference that is both simple and training-free, yet effectively suppresses hallucinations. This method leverages local visual prior information as a value function to correct the decoding process. Additionally, we observe that the impact of the local visual prior on model performance is more pronounced in scenarios with high levels of image noise. Notably, LPS is a plug-and-play approach that is compatible with various models. Extensive experiments on widely used hallucination benchmarks and noisy data demonstrate that LPS significantly reduces the incidence of hallucinations compared to the baseline, showing exceptional performance, particularly in noisy settings.
Authors: Ruoxuan Zhang, Jidong Gao, Bin Wen, Hongxia Xie, Chenming Zhang, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants. However, existing datasets lack fine-grained alignment between recipe goals, step-wise instructions, and visual content. We present RecipeGen, the first large-scale, real-world benchmark for recipe-based Text-to-Image (T2I), Image-to-Video (I2V), and Text-to-Video (T2V) generation. RecipeGen contains 26,453 recipes, 196,724 images, and 4,491 videos, covering diverse ingredients, cooking procedures, styles, and dish types. We further propose domain-specific evaluation metrics to assess ingredient fidelity and interaction modeling, benchmark representative T2I, I2V, and T2V models, and provide insights for future recipe generation models. Project page is available now.
Authors: Mingqi Gao, Haoran Duan, Tianlu Zhang, Jungong Han
Abstract: In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating these signals in a unified framework, we achieve strong segmentation performance. On the VISOR test set, our method reaches a J&F score of 90.1%.
Authors: Ziyu Yue, Ruixi You, Feng Xu
Abstract: To translate synthetic aperture radar (SAR) image into interpretable forms for human understanding is the ultimate goal of SAR advanced information retrieval. Existing methods mainly focus on 3D surface reconstruction or local geometric feature extraction of targets, neglecting the role of structural modeling in capturing semantic information. This paper proposes a novel task: SAR target structure recovery, which aims to infer the components of a target and the structural relationships between its components, specifically symmetry and adjacency, from a single-view SAR image. Through learning the structural consistency and geometric diversity across the same type of targets as observed in different SAR images, it aims to derive the semantic representation of target directly from its 2D SAR image. To solve this challenging task, a two-step algorithmic framework based on structural descriptors is developed. Specifically, in the training phase, it first detects 2D keypoints from real SAR images, and then learns the mapping from these keypoints to 3D hierarchical structures using simulated data. During the testing phase, these two steps are integrated to infer the 3D structure from real SAR images. Experimental results validated the effectiveness of each step and demonstrated, for the first time, that 3D semantic structural representation of aircraft targets can be directly derived from a single-view SAR image.
Authors: Nidheesh Gorthi, Kartik Thakral, Rishabh Ranjan, Richa Singh, Mayank Vatsa
Abstract: Biometric authentication systems are increasingly being deployed in critical applications, but they remain susceptible to spoofing. Since most of the research efforts focus on modality-specific anti-spoofing techniques, building a unified, resource-efficient solution across multiple biometric modalities remains a challenge. To address this, we propose LitMAS, a $\textbf{Li}$gh$\textbf{t}$ weight and generalizable $\textbf{M}$ulti-modal $\textbf{A}$nti-$\textbf{S}$poofing framework designed to detect spoofing attacks in speech, face, iris, and fingerprint-based biometric systems. At the core of LitMAS is a Modality-Aligned Concentration Loss, which enhances inter-class separability while preserving cross-modal consistency and enabling robust spoof detection across diverse biometric traits. With just 6M parameters, LitMAS surpasses state-of-the-art methods by $1.36\%$ in average EER across seven datasets, demonstrating high efficiency, strong generalizability, and suitability for edge deployment. Code and trained models are available at https://github.com/IAB-IITJ/LitMAS.
Authors: Mohammad-Maher Nakshbandi, Ziad Sharawy, Dorian Cojocaru, Sorin Grigorescu
Abstract: In this study, we introduce LoopDB, which is a challenging loop closure dataset comprising over 1000 images captured across diverse environments, including parks, indoor scenes, parking spaces, as well as centered around individual objects. Each scene is represented by a sequence of five consecutive images. The dataset was collected using a high resolution camera, providing suitable imagery for benchmarking the accuracy of loop closure algorithms, typically used in simultaneous localization and mapping. As ground truth information, we provide computed rotations and translations between each consecutive images. Additional to its benchmarking goal, the dataset can be used to train and fine-tune loop closure methods based on deep neural networks. LoopDB is publicly available at https://github.com/RovisLab/LoopDB.
Authors: Lennart Bastian, Mohammad Rashed, Nassir Navab, Tolga Birdal
Abstract: Tracking and forecasting the rotation of objects is fundamental in computer vision and robotics, yet SO(3) extrapolation remains challenging as (1) sensor observations can be noisy and sparse, (2) motion patterns can be governed by complex dynamics, and (3) application settings can demand long-term forecasting. This work proposes modeling continuous-time rotational object dynamics on $SO(3)$ using Neural Controlled Differential Equations guided by Savitzky-Golay paths. Unlike existing methods that rely on simplified motion assumptions, our method learns a general latent dynamical system of the underlying object trajectory while respecting the geometric structure of rotations. Experimental results on real-world data demonstrate compelling forecasting capabilities compared to existing approaches.
Authors: Mohammad Ali Rezaei, Helia Hajikazem, Saeed Khanehgir, Mahdi Javanmardi
Abstract: While diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality stylization. This limitation is particularly acute for images where faces are small or exhibit significant camera-to-face distances, frequently leading to inadequate identity preservation. To address this, we introduce a novel, training-free framework for identity-preserved stylized image synthesis using diffusion models. Key contributions include: (1) the "Mosaic Restored Content Image" technique, significantly enhancing identity retention, especially in complex scenes; and (2) a training-free content consistency loss that enhances the preservation of fine-grained content details by directing more attention to the original image during stylization. Our experiments reveal that the proposed approach substantially surpasses the baseline model in concurrently maintaining high stylistic fidelity and robust identity integrity, particularly under conditions of small facial regions or significant camera-to-face distances, all without necessitating model retraining or fine-tuning.
Authors: Chao Yin, Hao Li, Kequan Yang, Jide Li, Pinpin Zhu, Xiaoqiang Li
Abstract: While promptable segmentation (\textit{e.g.}, SAM) has shown promise for various segmentation tasks, it still requires manual visual prompts for each object to be segmented. In contrast, task-generic promptable segmentation aims to reduce the need for such detailed prompts by employing only a task-generic prompt to guide segmentation across all test samples. However, when applied to Camouflaged Object Segmentation (COS), current methods still face two critical issues: 1) \textit{\textbf{semantic ambiguity in getting instance-specific text prompts}}, which arises from insufficient discriminative cues in holistic captions, leading to foreground-background confusion; 2) \textit{\textbf{semantic discrepancy combined with spatial separation in getting instance-specific visual prompts}}, which results from global background sampling far from object boundaries with low feature correlation, causing SAM to segment irrelevant regions. To address the issues above, we propose \textbf{RDVP-MSD}, a novel training-free test-time adaptation framework that synergizes \textbf{R}egion-constrained \textbf{D}ual-stream \textbf{V}isual \textbf{P}rompting (RDVP) via \textbf{M}ultimodal \textbf{S}tepwise \textbf{D}ecomposition Chain of Thought (MSD-CoT). MSD-CoT progressively disentangles image captions to eliminate semantic ambiguity, while RDVP injects spatial constraints into visual prompting and independently samples visual prompts for foreground and background points, effectively mitigating semantic discrepancy and spatial separation. Without requiring any training or supervision, RDVP-MSD achieves a state-of-the-art segmentation result on multiple COS benchmarks and delivers a faster inference speed than previous methods, demonstrating significantly improved accuracy and efficiency. The codes will be available at \href{https://github.com/ycyinchao/RDVP-MSD}{https://github.com/ycyinchao/RDVP-MSD}
URLs: https://github.com/ycyinchao/RDVP-MSD, https://github.com/ycyinchao/RDVP-MSD
Authors: Chenlu Zhan, Yufei Zhang, Gaoang Wang, Hongwei Wang
Abstract: Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a unified 3D representation, leading to view inconsistencies. Additionally, inherent open-vocabulary challenges cause inconsistencies in object and relational descriptions, impeding hierarchical semantic understanding. In this paper, we propose Hi-LSplat, a view-consistent Hierarchical Language Gaussian Splatting work for 3D open-vocabulary querying. To achieve view-consistent 3D hierarchical semantics, we first lift 2D features to 3D features by constructing a 3D hierarchical semantic tree with layered instance clustering, which addresses the view inconsistency issue caused by 2D semantic features. Besides, we introduce instance-wise and part-wise contrastive losses to capture all-sided hierarchical semantic representations. Notably, we construct two hierarchical semantic datasets to better assess the model's ability to distinguish different semantic levels. Extensive experiments highlight our method's superiority in 3D open-vocabulary segmentation and localization. Its strong performance on hierarchical semantic datasets underscores its ability to capture complex hierarchical semantics within 3D scenes.
Authors: Qi Li, Liangzhi Li, Zhouqiang Jiang, Bowen Wang, Keke Tang
Abstract: Visual Prompting (VP), an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a robust source model: Can the robustness of the source model be successfully inherited? Does VP also encounter the same trade-off between robustness and generalization ability as the source model during this process? If such a trade-off exists, is there a strategy specifically tailored to VP to mitigate this limitation? In this paper, we thoroughly explore these three questions for the first time and provide affirmative answers to them. To mitigate the trade-off faced by VP, we propose a strategy called Prompt Boundary Loosening (PBL). As a lightweight, plug-and-play strategy naturally compatible with VP, PBL effectively ensures the successful inheritance of robustness when the source model is a robust model, while significantly enhancing VP's generalization ability across various downstream datasets. Extensive experiments across various datasets show that our findings are universal and demonstrate the significant benefits of the proposed strategy.
Authors: Chenfei Yuan, Nanshan Jia, Hangqi Li, Peter W. Glynn, Zeyu Zheng
Abstract: We provide an attention-level control method for the task of coupled image generation, where "coupled" means that multiple simultaneously generated images are expected to have the same or very similar backgrounds. While backgrounds coupled, the centered objects in the generated images are still expected to enjoy the flexibility raised from different text prompts. The proposed method disentangles the background and entity components in the model's cross-attention modules, attached with a sequence of time-varying weight control parameters depending on the time step of sampling. We optimize this sequence of weight control parameters with a combined objective that assesses how coupled the backgrounds are as well as text-to-image alignment and overall visual quality. Empirical results demonstrate that our method outperforms existing approaches across these criteria.
Authors: Guankun Wang, Rui Tang, Mengya Xu, Long Bai, Huxin Gao, Hongliang Ren
Abstract: Endoscopic surgery is the gold standard for robotic-assisted minimally invasive surgery, offering significant advantages in early disease detection and precise interventions. However, the complexity of surgical scenes, characterized by high variability in different surgical activity scenarios and confused image features between targets and the background, presents challenges for surgical environment understanding. Traditional deep learning models often struggle with cross-activity interference, leading to suboptimal performance in each downstream task. To address this limitation, we explore multi-task learning, which utilizes the interrelated features between tasks to enhance overall task performance. In this paper, we propose EndoARSS, a novel multi-task learning framework specifically designed for endoscopy surgery activity recognition and semantic segmentation. Built upon the DINOv2 foundation model, our approach integrates Low-Rank Adaptation to facilitate efficient fine-tuning while incorporating Task Efficient Shared Low-Rank Adapters to mitigate gradient conflicts across diverse tasks. Additionally, we introduce the Spatially-Aware Multi-Scale Attention that enhances feature representation discrimination by enabling cross-spatial learning of global information. In order to evaluate the effectiveness of our framework, we present three novel datasets, MTLESD, MTLEndovis and MTLEndovis-Gen, tailored for endoscopic surgery scenarios with detailed annotations for both activity recognition and semantic segmentation tasks. Extensive experiments demonstrate that EndoARSS achieves remarkable performance across multiple benchmarks, significantly improving both accuracy and robustness in comparison to existing models. These results underscore the potential of EndoARSS to advance AI-driven endoscopic surgical systems, offering valuable insights for enhancing surgical safety and efficiency.
Authors: Zelin He, Sarah Alnegheimish, Matthew Reimherr
Abstract: Time-series anomaly detection (TSAD) has played a vital role in a variety of fields, including healthcare, finance, and industrial monitoring. Prior methods, which mainly focus on training domain-specific models on numerical data, lack the visual-temporal reasoning capacity that human experts have to identify contextual anomalies. To fill this gap, we explore a solution based on vision language models (VLMs). Recent studies have shown the ability of VLMs for visual reasoning tasks, yet their direct application to time series has fallen short on both accuracy and efficiency. To harness the power of VLMs for TSAD, we propose a two-stage solution, with (1) ViT4TS, a vision-screening stage built on a relatively lightweight pretrained vision encoder, which leverages 2-D time-series representations to accurately localize candidate anomalies; (2) VLM4TS, a VLM-based stage that integrates global temporal context and VLM reasoning capacity to refine the detection upon the candidates provided by ViT4TS. We show that without any time-series training, VLM4TS outperforms time-series pretrained and from-scratch baselines in most cases, yielding a 24.6 percent improvement in F1-max score over the best baseline. Moreover, VLM4TS also consistently outperforms existing language-model-based TSAD methods and is on average 36 times more efficient in token usage.
Authors: Yangkai Lin, Jiabao Lei, Kui jia
Abstract: In recent years, there has been a growing demand to stylize a given 3D scene to align with the artistic style of reference images for creative purposes. While 3D Gaussian Splatting(GS) has emerged as a promising and efficient method for realistic 3D scene modeling, there remains a challenge in adapting it to stylize 3D GS to match with multiple styles through automatic local style transfer or manual designation, while maintaining memory efficiency for stylization training. In this paper, we introduce a novel 3D GS stylization solution termed Multi-StyleGS to tackle these challenges. In particular, we employ a bipartite matching mechanism to au tomatically identify correspondences between the style images and the local regions of the rendered images. To facilitate local style transfer, we introduce a novel semantic style loss function that employs a segmentation network to apply distinct styles to various objects of the scene and propose a local-global feature matching to enhance the multi-view consistency. Furthermore, this technique can achieve memory efficient training, more texture details and better color match. To better assign a robust semantic label to each Gaussian, we propose several techniques to regularize the segmentation network. As demonstrated by our comprehensive experiments, our approach outperforms existing ones in producing plausible stylization results and offering flexible editing.
Authors: Sara M. Cerqueira, Manuel Palermo, Cristina P. Santos
Abstract: Inertial-based Motion capture system has been attracting growing attention due to its wearability and unsconstrained use. However, accurate human joint estimation demands several complex and expertise demanding steps, which leads to expensive software such as the state-of-the-art MVN Awinda from Xsens Technologies. This work aims to study the use of Neural Networks to abstract the complex biomechanical models and analytical mathematics required for pose estimation. Thus, it presents a comparison of different Neural Network architectures and methodologies to understand how accurately these methods can estimate human pose, using both low cost(MPU9250) and high end (Mtw Awinda) Magnetic, Angular Rate, and Gravity (MARG) sensors. The most efficient method was the Hybrid LSTM-Madgwick detached, which achieved an Quaternion Angle distance error of 7.96, using Mtw Awinda data. Also, an ablation study was conducted to study the impact of data augmentation, output representation, window size, loss function and magnetometer data on the pose estimation error. This work indicates that Neural Networks can be trained to estimate human pose, with results comparable to the state-of-the-art fusion filters.
Authors: John Waithaka, Moise Busogi
Abstract: Semantic segmentation of satellite imagery is crucial for Earth observation applications, but remains constrained by limited labelled training data. While self-supervised pretraining methods like Masked Autoencoders (MAE) have shown promise, they focus on reconstruction rather than localisation-a fundamental aspect of segmentation tasks. We propose adapting LOCA (Location-aware), a position prediction self-supervised learning method, for multimodal satellite imagery semantic segmentation. Our approach addresses the unique challenges of satellite data by extending SatMAE's channel grouping from multispectral to multimodal data, enabling effective handling of multiple modalities, and introducing same-group attention masking to encourage cross-modal interaction during pretraining. The method uses relative patch position prediction, encouraging spatial reasoning for localisation rather than reconstruction. We evaluate our approach on the Sen1Floods11 flood mapping dataset, where it significantly outperforms existing reconstruction-based self-supervised learning methods for satellite imagery. Our results demonstrate that position prediction tasks, when properly adapted for multimodal satellite imagery, learn representations more effective for satellite image semantic segmentation than reconstruction-based approaches.
Authors: Markus Knoche, Daan de Geus, Bastian Leibe
Abstract: Predicting the motion of other agents in a scene is highly relevant for autonomous driving, as it allows a self-driving car to anticipate. Inspired by the success of decoder-only models for language modeling, we propose DONUT, a Decoder-Only Network for Unrolling Trajectories. Different from existing encoder-decoder forecasting models, we encode historical trajectories and predict future trajectories with a single autoregressive model. This allows the model to make iterative predictions in a consistent manner, and ensures that the model is always provided with up-to-date information, enhancing the performance. Furthermore, inspired by multi-token prediction for language modeling, we introduce an 'overprediction' strategy that gives the network the auxiliary task of predicting trajectories at longer temporal horizons. This allows the model to better anticipate the future, and further improves the performance. With experiments, we demonstrate that our decoder-only approach outperforms the encoder-decoder baseline, and achieves new state-of-the-art results on the Argoverse 2 single-agent motion forecasting benchmark.
Authors: Chaoyang Wang, Zeyu Zhang, Haiyun Jiang
Abstract: Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement Learning (RL) fine-tuning (e.g., GRPO). However, current RL approaches sample action groups solely from the policy model itself, which limits the upper boundary of the model's reasoning capability and leads to inefficient training. To address these limitations, this paper proposes a novel RL framework called \textbf{Vision-EKIPL}. The core of this framework lies in introducing high-quality actions generated by external auxiliary models during the RL training process to guide the optimization of the policy model. The policy learning with knowledge infusion from external models significantly expands the model's exploration space, effectively improves the reasoning boundary, and substantially accelerates training convergence speed and efficiency. Experimental results demonstrate that our proposed Vision-EKIPL achieved up to a 5\% performance improvement on the Reason-RFT-CoT Benchmark compared to the state-of-the-art (SOTA). It reveals that Vision-EKIPL can overcome the limitations of traditional RL methods, significantly enhance the visual reasoning performance of MLLMs, and provide a new effective paradigm for research in this field.
Authors: Junyu Liu, Jianfeng Ren, Sunhong Liang, Xudong Jiang
Abstract: Face recognition using 3D point clouds is gaining growing interest, while raw point clouds often contain a significant amount of noise due to imperfect sensors. In this paper, an end-to-end 3D face recognition on a noisy point cloud is proposed, which synergistically integrates the denoising and recognition modules. Specifically, a Conditional Generative Adversarial Network on Three Orthogonal Planes (cGAN-TOP) is designed to effectively remove the noise in the point cloud, and recover the underlying features for subsequent recognition. A Linked Dynamic Graph Convolutional Neural Network (LDGCNN) is then adapted to recognize faces from the processed point cloud, which hierarchically links both the local point features and neighboring features of multiple scales. The proposed method is validated on the Bosphorus dataset. It significantly improves the recognition accuracy under all noise settings, with a maximum gain of 14.81%.
Authors: Wafaa Kasri, Yassine Himeur, Abigail Copiaco, Wathiq Mansoor, Ammar Albanna, Valsamma Eapen
Abstract: Accurate Autism Spectrum Disorder (ASD) diagnosis is vital for early intervention. This study presents a hybrid deep learning framework combining Vision Transformers (ViT) and Vision Mamba to detect ASD using eye-tracking data. The model uses attention-based fusion to integrate visual, speech, and facial cues, capturing both spatial and temporal dynamics. Unlike traditional handcrafted methods, it applies state-of-the-art deep learning and explainable AI techniques to enhance diagnostic accuracy and transparency. Tested on the Saliency4ASD dataset, the proposed ViT-Mamba model outperformed existing methods, achieving 0.96 accuracy, 0.95 F1-score, 0.97 sensitivity, and 0.94 specificity. These findings show the model's promise for scalable, interpretable ASD screening, especially in resource-constrained or remote clinical settings where access to expert diagnosis is limited.
Authors: Reese Kneeland, Paul S. Scotti, Ghislain St-Yves, Jesse Breedlove, Kendrick Kay, Thomas Naselaris
Abstract: We release NSD-Imagery, a benchmark dataset of human fMRI activity paired with mental images, to complement the existing Natural Scenes Dataset (NSD), a large-scale dataset of fMRI activity paired with seen images that enabled unprecedented improvements in fMRI-to-image reconstruction efforts. Recent models trained on NSD have been evaluated only on seen image reconstruction. Using NSD-Imagery, it is possible to assess how well these models perform on mental image reconstruction. This is a challenging generalization requirement because mental images are encoded in human brain activity with relatively lower signal-to-noise and spatial resolution; however, generalization from seen to mental imagery is critical for real-world applications in medical domains and brain-computer interfaces, where the desired information is always internally generated. We provide benchmarks for a suite of recent NSD-trained open-source visual decoding models (MindEye1, MindEye2, Brain Diffuser, iCNN, Takagi et al.) on NSD-Imagery, and show that the performance of decoding methods on mental images is largely decoupled from performance on vision reconstruction. We further demonstrate that architectural choices significantly impact cross-decoding performance: models employing simple linear decoding architectures and multimodal feature decoding generalize better to mental imagery, while complex architectures tend to overfit visual training data. Our findings indicate that mental imagery datasets are critical for the development of practical applications, and establish NSD-Imagery as a useful resource for better aligning visual decoding methods with this goal.
Authors: Nima Jamali, Matina Mahdizadeh Sani, Hanieh Naderi, Shohreh Kasaei
Abstract: Deep neural networks (DNNs) have demonstrated remarkable performance in analyzing 3D point cloud data. However, their vulnerability to adversarial attacks-such as point dropping, shifting, and adding-poses a critical challenge to the reliability of 3D vision systems. These attacks can compromise the semantic and structural integrity of point clouds, rendering many existing defense mechanisms ineffective. To address this issue, a defense strategy named KNN-Defense is proposed, grounded in the manifold assumption and nearest-neighbor search in feature space. Instead of reconstructing surface geometry or enforcing uniform point distributions, the method restores perturbed inputs by leveraging the semantic similarity of neighboring samples from the training set. KNN-Defense is lightweight and computationally efficient, enabling fast inference and making it suitable for real-time and practical applications. Empirical results on the ModelNet40 dataset demonstrated that KNN-Defense significantly improves robustness across various attack types. In particular, under point-dropping attacks-where many existing methods underperform due to the targeted removal of critical points-the proposed method achieves accuracy gains of 20.1%, 3.6%, 3.44%, and 7.74% on PointNet, PointNet++, DGCNN, and PCT, respectively. These findings suggest that KNN-Defense offers a scalable and effective solution for enhancing the adversarial resilience of 3D point cloud classifiers. (An open-source implementation of the method, including code and data, is available at https://github.com/nimajam41/3d-knn-defense).
Authors: Vladimir Yugay, Thies Kersten, Luca Carlone, Theo Gevers, Martin R. Oswald, Lukas Schmid
Abstract: Mapping systems with novel view synthesis (NVS) capabilities are widely used in computer vision, with augmented reality, robotics, and autonomous driving applications. Most notably, 3D Gaussian Splatting-based systems show high NVS performance; however, many current approaches are limited to static scenes. While recent works have started addressing short-term dynamics (motion within the view of the camera), long-term dynamics (the scene evolving through changes out of view) remain less explored. To overcome this limitation, we introduce a dynamic scene adaptation mechanism that continuously updates the 3D representation to reflect the latest changes. In addition, since maintaining geometric and semantic consistency remains challenging due to stale observations disrupting the reconstruction process, we propose a novel keyframe management mechanism that discards outdated observations while preserving as much information as possible. We evaluate Gaussian Mapping for Evolving Scenes (GaME) on both synthetic and real-world datasets and find it to be more accurate than the state of the art.
Authors: Olivier Papillon, Rafik Goubran, James Green, Julien Larivi\`ere-Chartier, Caitlin Higginson, Frank Knoefel, R\'ebecca Robillard
Abstract: Accurate sleep stage classification is essential for diagnosing sleep disorders, particularly in aging populations. While traditional polysomnography (PSG) relies on electroencephalography (EEG) as the gold standard, its complexity and need for specialized equipment make home-based sleep monitoring challenging. To address this limitation, we investigate the use of electrooculography (EOG) and pressure-sensitive mats (PSM) as less obtrusive alternatives for five-stage sleep-wake classification. This study introduces a novel approach that leverages ImageBind, a multimodal embedding deep learning model, to integrate PSM data with dual-channel EOG signals for sleep stage classification. Our method is the first reported approach that fuses PSM and EOG data for sleep stage classification with ImageBind. Our results demonstrate that fine-tuning ImageBind significantly improves classification accuracy, outperforming existing models based on single-channel EOG (DeepSleepNet), exclusively PSM data (ViViT), and other multimodal deep learning approaches (MBT). Notably, the model also achieved strong performance without fine-tuning, highlighting its adaptability to specific tasks with limited labeled data, making it particularly advantageous for medical applications. We evaluated our method using 85 nights of patient recordings from a sleep clinic. Our findings suggest that pre-trained multimodal embedding models, even those originally developed for non-medical domains, can be effectively adapted for sleep staging, with accuracies approaching systems that require complex EEG data.
Authors: Carl Brander, Giovanni Cioffi, Nico Messikommer, Davide Scaramuzza
Abstract: Current smart glasses equipped with RGB cameras struggle to perceive the environment in low-light and high-speed motion scenarios due to motion blur and the limited dynamic range of frame cameras. Additionally, capturing dense images with a frame camera requires large bandwidth and power consumption, consequently draining the battery faster. These challenges are especially relevant for developing algorithms that can read text from images. In this work, we propose a novel event-based Optical Character Recognition (OCR) approach for smart glasses. By using the eye gaze of the user, we foveate the event stream to significantly reduce bandwidth by around 98% while exploiting the benefits of event cameras in high-dynamic and fast scenes. Our proposed method performs deep binary reconstruction trained on synthetic data and leverages multimodal LLMs for OCR, outperforming traditional OCR solutions. Our results demonstrate the ability to read text in low light environments where RGB cameras struggle while using up to 2400 times less bandwidth than a wearable RGB camera.
Authors: George Lydakis, Alexander Hermans, Ali Athar, Daan de Geus, Bastian Leibe
Abstract: Research into Video Large Language Models (LLMs) has progressed rapidly, with numerous models and benchmarks emerging in just a few years. Typically, these models are initialized with a pretrained text-only LLM and finetuned on both image- and video-caption datasets. In this paper, we present findings indicating that Video LLMs are more capable of temporal reasoning after image-only training than one would assume, and that improvements from video-specific training are surprisingly small. Specifically, we show that image-trained versions of two LLMs trained with the recent LongVU algorithm perform significantly above chance level on TVBench, a temporal reasoning benchmark. Additionally, we introduce a simple finetuning scheme involving sequences of annotated images and questions targeting temporal capabilities. This baseline results in temporal reasoning performance close to, and occasionally higher than, what is achieved by video-trained LLMs. This suggests suboptimal utilization of rich temporal features found in real video by current models. Our analysis motivates further research into the mechanisms that allow image-trained LLMs to perform temporal reasoning, as well as into the bottlenecks that render current video training schemes inefficient.
Authors: Mellon M. Zhang, Glen Chou, Saibal Mukhopadhyay
Abstract: Accurate and efficient object detection is essential for autonomous vehicles, where real-time perception requires low latency and high throughput. LiDAR sensors provide robust depth information, but conventional methods process full 360{\deg} scans in a single pass, introducing significant delay. Streaming approaches address this by sequentially processing partial scans in the native polar coordinate system, yet they rely on translation-invariant convolutions that are misaligned with polar geometry -- resulting in degraded performance or requiring complex distortion mitigation. Recent Mamba-based state space models (SSMs) have shown promise for LiDAR perception, but only in the full-scan setting, relying on geometric serialization and positional embeddings that are memory-intensive and ill-suited to streaming. We propose Polar Hierarchical Mamba (PHiM), a novel SSM architecture designed for polar-coordinate streaming LiDAR. PHiM uses local bidirectional Mamba blocks for intra-sector spatial encoding and a global forward Mamba for inter-sector temporal modeling, replacing convolutions and positional encodings with distortion-aware, dimensionally-decomposed operations. PHiM sets a new state-of-the-art among streaming detectors on the Waymo Open Dataset, outperforming the previous best by 10\% and matching full-scan baselines at twice the throughput. Code will be available at https://github.com/meilongzhang/Polar-Hierarchical-Mamba .
URLs: https://github.com/meilongzhang/Polar-Hierarchical-Mamba
Authors: Ying Shen, Zhiyang Xu, Jiuhai Chen, Shizhe Diao, Jiaxin Zhang, Yuguang Yao, Joy Rimchala, Ismini Lourentzou, Lifu Huang
Abstract: Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models typically require extensive pretraining and struggle to achieve the same level of performance compared to models dedicated to each task. Additionally, many of these models suffer from slow image generation speeds, limiting their practical deployment in real-time or resource-constrained settings. In this work, we propose Layerwise Timestep-Expert Flow-based Transformer (LaTtE-Flow), a novel and efficient architecture that unifies image understanding and generation within a single multimodal model. LaTtE-Flow builds upon powerful pretrained Vision-Language Models (VLMs) to inherit strong multimodal understanding capabilities, and extends them with a novel Layerwise Timestep Experts flow-based architecture for efficient image generation. LaTtE-Flow distributes the flow-matching process across specialized groups of Transformer layers, each responsible for a distinct subset of timesteps. This design significantly improves sampling efficiency by activating only a small subset of layers at each sampling timestep. To further enhance performance, we propose a Timestep-Conditioned Residual Attention mechanism for efficient information reuse across layers. Experiments demonstrate that LaTtE-Flow achieves strong performance on multimodal understanding tasks, while achieving competitive image generation quality with around 6x faster inference speed compared to recent unified multimodal models.
Authors: Maciej Zyrek, Tomasz Tarasiewicz, Jakub Sadel, Aleksandra Krzywon, Michal Kawulok
Abstract: Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with low-resolution images obtained by degrading and downsampling high-resolution ones -- they frequently fail to generalize to real-world settings, such as document scans, which are affected by complex degradations and semantic variability. In this study, we introduce a task-driven, multi-task learning framework for training a super-resolution network specifically optimized for optical character recognition tasks. We propose to incorporate auxiliary loss functions derived from high-level vision tasks, including text detection using the connectionist text proposal network, text recognition via a convolutional recurrent neural network, keypoints localization using Key.Net, and hue consistency. To balance these diverse objectives, we employ dynamic weight averaging mechanism, which adaptively adjusts the relative importance of each loss term based on its convergence behavior. We validate our approach upon the SRResNet architecture, which is a well-established technique for single-image super-resolution. Experimental evaluations on both simulated and real-world scanned document datasets demonstrate that the proposed approach improves text detection, measured with intersection over union, while preserving overall image fidelity. These findings underscore the value of multi-objective optimization in super-resolution models for bridging the gap between simulated training regimes and practical deployment in real-world scenarios.
Authors: Jingyuan Qi, Zhiyang Xu, Qifan Wang, Lifu Huang
Abstract: We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single, static retrieval before generation and condition the entire generation on fixed reference images, AR-RAG performs context-aware retrievals at each generation step, using prior-generated patches as queries to retrieve and incorporate the most relevant patch-level visual references, enabling the model to respond to evolving generation needs while avoiding limitations (e.g., over-copying, stylistic bias, etc.) prevalent in existing methods. To realize AR-RAG, we propose two parallel frameworks: (1) Distribution-Augmentation in Decoding (DAiD), a training-free plug-and-use decoding strategy that directly merges the distribution of model-predicted patches with the distribution of retrieved patches, and (2) Feature-Augmentation in Decoding (FAiD), a parameter-efficient fine-tuning method that progressively smooths the features of retrieved patches via multi-scale convolution operations and leverages them to augment the image generation process. We validate the effectiveness of AR-RAG on widely adopted benchmarks, including Midjourney-30K, GenEval and DPG-Bench, demonstrating significant performance gains over state-of-the-art image generation models.
Authors: Siyuan Jing, Guangxue Wang, Haoyang Zhai, Qin Tao, Jun Yang, Bing Wang, Peng Jin
Abstract: Due to the emergence of many sign language datasets, isolated sign language recognition (ISLR) has made significant progress in recent years. In addition, the development of various advanced deep neural networks is another reason for this breakthrough. However, challenges remain in applying the technique in the real world. First, existing sign language datasets do not cover the whole sign vocabulary. Second, most of the sign language datasets provide only single view RGB videos, which makes it difficult to handle hand occlusions when performing ISLR. To fill this gap, this paper presents a dual-view sign language dataset for ISLR named NationalCSL-DP, which fully covers the Chinese national sign language vocabulary. The dataset consists of 134140 sign videos recorded by ten signers with respect to two vertical views, namely, the front side and the left side. Furthermore, a CNN transformer network is also proposed as a strong baseline and an extremely simple but effective fusion strategy for prediction. Extensive experiments were conducted to prove the effectiveness of the datasets as well as the baseline. The results show that the proposed fusion strategy can significantly increase the performance of the ISLR, but it is not easy for the sequence-to-sequence model, regardless of whether the early-fusion or late-fusion strategy is applied, to learn the complementary features from the sign videos of two vertical views.
Authors: Pengfei Zhao, Rongbo Luan, Wei Zhang, Peng Wu, Sifeng He
Abstract: Despite Contrastive Language-Image Pretraining (CLIP)'s remarkable capability to retrieve content across modalities, a substantial modality gap persists in its feature space. Intriguingly, we discover that off-the-shelf MLLMs (Multimodal Large Language Models) demonstrate powerful inherent modality alignment properties. While recent MLLM-based retrievers with unified architectures partially mitigate this gap, their reliance on coarse modality alignment mechanisms fundamentally limits their potential. In this work, We introduce MAPLE (Modality-Aligned Preference Learning for Embeddings), a novel framework that leverages the fine grained alignment priors inherent in MLLM to guide cross modal representation learning. MAPLE formulates the learning process as reinforcement learning with two key components: (1) Automatic preference data construction using off-the-shelf MLLM, and (2) a new Relative Preference Alignment (RPA) loss, which adapts Direct Preference Optimization (DPO) to the embedding learning setting. Experimental results show that our preference-guided alignment achieves substantial gains in fine-grained cross-modal retrieval, underscoring its effectiveness in handling nuanced semantic distinctions.
Authors: Binxiao Huang, Zhihao Li, Shiyong Liu, Xiao Tang, Jiajun Tang, Jiaqi Lin, Yuxin Cheng, Zhenyu Chen, Xiaofei Wu, Ngai Wong
Abstract: 3D Gaussian splatting (3DGS) has demonstrated exceptional performance in image-based 3D reconstruction and real-time rendering. However, regions with complex textures require numerous Gaussians to capture significant color variations accurately, leading to inefficiencies in rendering speed. To address this challenge, we introduce a hybrid representation for indoor scenes that combines 3DGS with textured meshes. Our approach uses textured meshes to handle texture-rich flat areas, while retaining Gaussians to model intricate geometries. The proposed method begins by pruning and refining the extracted mesh to eliminate geometrically complex regions. We then employ a joint optimization for 3DGS and mesh, incorporating a warm-up strategy and transmittance-aware supervision to balance their contributions seamlessly.Extensive experiments demonstrate that the hybrid representation maintains comparable rendering quality and achieves superior frames per second FPS with fewer Gaussian primitives.
Authors: Yanting Gao, Yepeng Liu, Junming Liu, Qi Zhang, Hongyun Zhang, Duoqian Miao, Cairong Zhao
Abstract: Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak transferability in black-box settings due to overfitting. Existing methods improve transferability by diversifying perturbation inputs or applying uniform gradient regularization within surrogate models, yet they have not fully leveraged the shared and unique features of surrogate models trained on the same task, leading to suboptimal transfer performance. Therefore, enhancing perturbations of common information shared by surrogate models and suppressing those tied to individual characteristics offers an effective way to improve transferability. Accordingly, we propose a commonality-oriented gradient optimization strategy (COGO) consisting of two components: Commonality Enhancement (CE) and Individuality Suppression (IS). CE perturbs the mid-to-low frequency regions, leveraging the fact that ViTs trained on the same dataset tend to rely more on mid-to-low frequency information for classification. IS employs adaptive thresholds to evaluate the correlation between backpropagated gradients and model individuality, assigning weights to gradients accordingly. Extensive experiments demonstrate that COGO significantly improves the transfer success rates of adversarial attacks, outperforming current state-of-the-art methods.
Authors: Cong Guan, Jiacheng Ying, Yuya Ieiri, Osamu Yoshie
Abstract: Dual-camera super-resolution is highly practical for smartphone photography that primarily super-resolve the wide-angle images using the telephoto image as a reference. In this paper, we propose DM$^3$Net, a novel dual-camera super-resolution network based on Domain Modulation and Multi-scale Matching. To bridge the domain gap between the high-resolution domain and the degraded domain, we learn two compressed global representations from image pairs corresponding to the two domains. To enable reliable transfer of high-frequency structural details from the reference image, we design a multi-scale matching module that conducts patch-level feature matching and retrieval across multiple receptive fields to improve matching accuracy and robustness. Moreover, we also introduce Key Pruning to achieve a significant reduction in memory usage and inference time with little model performance sacrificed. Experimental results on three real-world datasets demonstrate that our DM$^3$Net outperforms the state-of-the-art approaches.
Authors: Xiaoya Zhang
Abstract: This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured outdoor environments collected from multiple robotic platforms. This problem was addressed by implementing Point Prompt Tuning (PPT) integrated with Point Transformer v3 (PTv3) backbone, enabling adaptive processing of heterogeneous LiDAR data through platform-specific conditioning and cross-dataset class alignment strategies. The model is trained without requiring additional external data. As a result, this approach achieved substantial performance improvements with mIoU increases of up to 22.59% on challenging platforms compared to the baseline PTv3 model, demonstrating the effectiveness of adaptive point cloud understanding for field robotics applications.
Authors: Yunxiao Shi, Hong Cai, Jisoo Jeong, Yinhao Zhu, Shizhong Han, Amin Ansari, Fatih Porikli
Abstract: 3D occupancy provides fine-grained 3D geometry and semantics for scene understanding which is critical for autonomous driving. Most existing methods, however, carry high compute costs, requiring dense 3D feature volume and cross-attention to effectively aggregate information. More recent works have adopted Bird's Eye View (BEV) or sparse points as scene representation with much reduced cost, but still suffer from their respective shortcomings. More concretely, BEV struggles with small objects that often experience significant information loss after being projected to the ground plane. On the other hand, points can flexibly model little objects in 3D, but is inefficient at capturing flat surfaces or large objects. To address these challenges, in this paper, we present a novel 3D occupancy prediction approach, BePo, which combines BEV and sparse points based representations. We propose a dual-branch design: a query-based sparse points branch and a BEV branch. The 3D information learned in the sparse points branch is shared with the BEV stream via cross-attention, which enriches the weakened signals of difficult objects on the BEV plane. The outputs of both branches are finally fused to generate predicted 3D occupancy. We conduct extensive experiments on the Occ3D-nuScenes and Occ3D-Waymo benchmarks that demonstrate the superiority of our proposed BePo. Moreover, BePo also delivers competitive inference speed when compared to the latest efficient approaches.
Authors: Wentao Zhao, Yihe Niu, Yanbo Wang, Tianchen Deng, Shenghai Yuan, Zhenli Wang, Rui Guo, Jingchuan Wang
Abstract: This work presents UNO, a unified monocular visual odometry framework that enables robust and adaptable pose estimation across diverse environments, platforms, and motion patterns. Unlike traditional methods that rely on deployment-specific tuning or predefined motion priors, our approach generalizes effectively across a wide range of real-world scenarios, including autonomous vehicles, aerial drones, mobile robots, and handheld devices. To this end, we introduce a Mixture-of-Experts strategy for local state estimation, with several specialized decoders that each handle a distinct class of ego-motion patterns. Moreover, we introduce a fully differentiable Gumbel-Softmax module that constructs a robust inter-frame correlation graph, selects the optimal expert decoder, and prunes erroneous estimates. These cues are then fed into a unified back-end that combines pre-trained, scale-independent depth priors with a lightweight bundling adjustment to enforce geometric consistency. We extensively evaluate our method on three major benchmark datasets: KITTI (outdoor/autonomous driving), EuRoC-MAV (indoor/aerial drones), and TUM-RGBD (indoor/handheld), demonstrating state-of-the-art performance.
Authors: Qiyu Hou, Jun Wang
Abstract: To address the challenges of table structure recognition, we propose a novel Split-Merge-based top-down model optimized for large, densely populated tables. Our approach formulates row and column splitting as sequence labeling tasks, utilizing dual Transformer encoders to capture feature interactions. The merging process is framed as a grid cell classification task, leveraging an additional Transformer encoder to ensure accurate and coherent merging. By eliminating unstable bounding box predictions, our method reduces resolution loss and computational complexity, achieving high accuracy while maintaining fast processing speed. Extensive experiments on FinTabNet and PubTabNet demonstrate the superiority of our model over existing approaches, particularly in real-world applications. Our method offers a robust, scalable, and efficient solution for large-scale table recognition, making it well-suited for industrial deployment.
Authors: Sanjoy Chowdhury, Mohamed Elmoghany, Yohan Abeysinghe, Junjie Fei, Sayan Nag, Salman Khan, Mohamed Elhoseiny, Dinesh Manocha
Abstract: Large multimodal models (LMMs) have shown remarkable progress in audio-visual understanding, yet they struggle with real-world scenarios that require complex reasoning across extensive video collections. Existing benchmarks for video question answering remain limited in scope, typically involving one clip per query, which falls short of representing the challenges of large-scale, audio-visual retrieval and reasoning encountered in practical applications. To bridge this gap, we introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer. To this end, we present AVHaystacks, an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task. Additionally, we propose a model-agnostic, multi-agent framework MAGNET to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystacks. To enable robust evaluation of multi-video retrieval and temporal grounding for optimal response generation, we introduce two new metrics, STEM, which captures alignment errors between a ground truth and a predicted step sequence and MTGS, to facilitate balanced and interpretable evaluation of segment-level grounding performance. Project: https://schowdhury671.github.io/magnet_project/
Authors: Yikun Ji, Hong Yan, Jun Lan, Huijia Zhu, Weiqiang Wang, Qi Fan, Liqing Zhang, Jianfu Zhang
Abstract: The rapid advancement of image generation technologies intensifies the demand for interpretable and robust detection methods. Although existing approaches often attain high accuracy, they typically operate as black boxes without providing human-understandable justifications. Multi-modal Large Language Models (MLLMs), while not originally intended for forgery detection, exhibit strong analytical and reasoning capabilities. When properly fine-tuned, they can effectively identify AI-generated images and offer meaningful explanations. However, existing MLLMs still struggle with hallucination and often fail to align their visual interpretations with actual image content and human reasoning. To bridge this gap, we construct a dataset of AI-generated images annotated with bounding boxes and descriptive captions that highlight synthesis artifacts, establishing a foundation for human-aligned visual-textual grounded reasoning. We then finetune MLLMs through a multi-stage optimization strategy that progressively balances the objectives of accurate detection, visual localization, and coherent textual explanation. The resulting model achieves superior performance in both detecting AI-generated images and localizing visual flaws, significantly outperforming baseline methods.
Authors: Zheng Wang, Kai Ying, Bin Xu, Chunjiao Wang, Cong Bai
Abstract: Accurate near-real-time precipitation retrieval has been enhanced by satellite-based technologies. However, infrared-based algorithms have low accuracy due to weak relations with surface precipitation, whereas passive microwave and radar-based methods are more accurate but limited in range. This challenge motivates the Precipitation Retrieval Expansion (PRE) task, which aims to enable accurate, infrared-based full-disc precipitation retrievals beyond the scanning swath. We introduce Multimodal Knowledge Expansion, a two-stage pipeline with the proposed PRE-Net model. In the Swath-Distilling stage, PRE-Net transfers knowledge from a multimodal data integration model to an infrared-based model within the scanning swath via Coordinated Masking and Wavelet Enhancement (CoMWE). In the Full-Disc Adaptation stage, Self-MaskTune refines predictions across the full disc by balancing multimodal and full-disc infrared knowledge. Experiments on the introduced PRE benchmark demonstrate that PRE-Net significantly advanced precipitation retrieval performance, outperforming leading products like PERSIANN-CCS, PDIR, and IMERG. The code will be available at https://github.com/Zjut-MultimediaPlus/PRE-Net.
Authors: Tarique Dahri, Zulfiqar Ali Memon, Zhenyu Yu, Mohd. Yamani Idna Idris, Sheheryar Khan, Sadiq Ahmad, Maged Shoman, Saddam Aziz, Rizwan Qureshi
Abstract: We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to intermediate feature maps, generating diverse self-supervised knowledge and enabling one-to-one transfer across different network stages. Our method achieves an average improvement of 4.54\% over the state-of-the-art PS-KD method and a 1.14% gain over SSKD on CIFAR-100, with a 0.32% improvement on ImageNet compared to HASSKD. Experiments on Tiny ImageNet and CIFAR-100 under few-shot learning scenarios also achieve state-of-the-art results. These findings demonstrate the effectiveness of our approach in enhancing model generalization and performance without the need for large over-parameterized teacher networks. Importantly, at the inference stage, all auxiliary classifiers can be removed, yielding no extra computational cost. This makes our model suitable for deploying small language models on affordable low-computing devices. Owing to its lightweight design and adaptability, our framework is particularly suitable for multimodal sensing and cyber-physical environments that require efficient and responsive inference. LSSKD facilitates the development of intelligent agents capable of learning from limited sensory data under weak supervision.
Authors: Zhenyu Liu, Huizhi Liang, Rajiv Ranjan, Zhanxing Zhu, Vaclav Snasel, Varun Ojha
Abstract: The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are (i) insufficient guidance of the target model via loss functions and (ii) non-collaborative adversarial generation. We, therefore, propose a dual regularization loss (D2R Loss) method and a collaborative adversarial generation (CAG) strategy for adversarial training. D2R loss includes two optimization steps. The adversarial distribution and clean distribution optimizations enhance the target model's robustness by leveraging the strengths of different loss functions obtained via a suitable function space exploration to focus more precisely on the target model's distribution. CAG generates adversarial samples using a gradient-based collaboration between guidance and target models. We conducted extensive experiments on three benchmark databases, including CIFAR-10, CIFAR-100, Tiny ImageNet, and two popular target models, WideResNet34-10 and PreActResNet18. Our results show that D2R loss with CAG produces highly robust models.
Authors: Anatol Garioud, S\'ebastien Giordano, Nicolas David, Nicolas Gonthier
Abstract: The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major processing and annotation challenges. To address this, the French National Institute of Geographical and Forest Information (IGN) is actively exploring innovative strategies to exploit diverse EO data, which require large annotated datasets. IGN introduces FLAIR-HUB, the largest multi-sensor land cover dataset with very-high-resolution (20 cm) annotations, covering 2528 km2 of France. It combines six aligned modalities: aerial imagery, Sentinel-1/2 time series, SPOT imagery, topographic data, and historical aerial images. Extensive benchmarks evaluate multimodal fusion and deep learning models (CNNs, transformers) for land cover or crop mapping and also explore multi-task learning. Results underscore the complexity of multimodal fusion and fine-grained classification, with best land cover performance (78.2% accuracy, 65.8% mIoU) achieved using nearly all modalities. FLAIR-HUB supports supervised and multimodal pretraining, with data and code available at https://ignf.github.io/FLAIR/flairhub.
Authors: Weiqi Yan, Lvhai Chen, Huaijia Kou, Shengchuan Zhang, Yan Zhang, Liujuan Cao
Abstract: Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.
Authors: Yangkai Lin, Jiabao Lei, Kui Jia
Abstract: Our project page: https://scutyklin.github.io/SceneLCM/. Automated generation of complex, interactive indoor scenes tailored to user prompt remains a formidable challenge. While existing methods achieve indoor scene synthesis, they struggle with rigid editing constraints, physical incoherence, excessive human effort, single-room limitations, and suboptimal material quality. To address these limitations, we propose SceneLCM, an end-to-end framework that synergizes Large Language Model (LLM) for layout design with Latent Consistency Model(LCM) for scene optimization. Our approach decomposes scene generation into four modular pipelines: (1) Layout Generation. We employ LLM-guided 3D spatial reasoning to convert textual descriptions into parametric blueprints(3D layout). And an iterative programmatic validation mechanism iteratively refines layout parameters through LLM-mediated dialogue loops; (2) Furniture Generation. SceneLCM employs Consistency Trajectory Sampling(CTS), a consistency distillation sampling loss guided by LCM, to form fast, semantically rich, and high-quality representations. We also offer two theoretical justification to demonstrate that our CTS loss is equivalent to consistency loss and its distillation error is bounded by the truncation error of the Euler solver; (3) Environment Optimization. We use a multiresolution texture field to encode the appearance of the scene, and optimize via CTS loss. To maintain cross-geometric texture coherence, we introduce a normal-aware cross-attention decoder to predict RGB by cross-attending to the anchors locations in geometrically heterogeneous instance. (4)Physically Editing. SceneLCM supports physically editing by integrating physical simulation, achieved persistent physical realism. Extensive experiments validate SceneLCM's superiority over state-of-the-art techniques, showing its wide-ranging potential for diverse applications.
Authors: Changhong Fu, Hua Lin, Haobo Zuo, Liangliang Yao, Liguo Zhang
Abstract: Text spotting for industrial panels is a key task for intelligent monitoring. However, achieving efficient and accurate text spotting for complex industrial panels remains challenging due to issues such as cross-scale localization and ambiguous boundaries in dense text regions. Moreover, most existing methods primarily focus on representing a single text shape, neglecting a comprehensive exploration of multi-scale feature information across different texts. To address these issues, this work proposes a novel multi-scale dense text spotter for edge AI-based vision system (EdgeSpotter) to achieve accurate and robust industrial panel monitoring. Specifically, a novel Transformer with efficient mixer is developed to learn the interdependencies among multi-level features, integrating multi-layer spatial and semantic cues. In addition, a new feature sampling with catmull-rom splines is designed, which explicitly encodes the shape, position, and semantic information of text, thereby alleviating missed detections and reducing recognition errors caused by multi-scale or dense text regions. Furthermore, a new benchmark dataset for industrial panel monitoring (IPM) is constructed. Extensive qualitative and quantitative evaluations on this challenging benchmark dataset validate the superior performance of the proposed method in different challenging panel monitoring tasks. Finally, practical tests based on the self-designed edge AI-based vision system demonstrate the practicality of the method. The code and demo will be available at https://github.com/vision4robotics/EdgeSpotter.
Authors: Prakriti Tripathi, Theertha Biju, Maniram Thota, Rakesh Lingam
Abstract: Industry partners provided a problem statement that involves classifying electronic waste using machine learning models that will be used by pick-and-place robots for waste segregation. We started by taking common electronic waste items, such as a mouse and charger, unsoldering them, and taking pictures to create a custom dataset. Then state-of-the art YOLOv11 model was trained and run to achieve 70 mAP in real-time. Mask-RCNN model was also trained and achieved 41 mAP. The model will be further integrated with pick-and-place robots to perform segregation of e-waste.
Authors: Huaize Liu, Wenzhang Sun, Qiyuan Zhang, Donglin Di, Biao Gong, Hao Li, Chen Wei, Changqing Zou
Abstract: Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall leads to excessive training costs for downstream tasks. To address this, we introduce Hi-VAE, an efficient video autoencoding framework that hierarchically encode coarse-to-fine motion representations of video dynamics and formulate the decoding process as a conditional generation task. Specifically, Hi-VAE decomposes video dynamics into two latent spaces: Global Motion, capturing overarching motion patterns, and Detailed Motion, encoding high-frequency spatial details. Using separate self-supervised motion encoders, we compress video latents into compact motion representations to reduce redundancy significantly. A conditional diffusion decoder then reconstructs videos by combining hierarchical global and detailed motions, enabling high-fidelity video reconstructions. Extensive experiments demonstrate that Hi-VAE achieves a high compression factor of 1428$\times$, almost 30$\times$ higher than baseline methods (e.g., Cosmos-VAE at 48$\times$), validating the efficiency of our approach. Meanwhile, Hi-VAE maintains high reconstruction quality at such high compression rates and performs effectively in downstream generative tasks. Moreover, Hi-VAE exhibits interpretability and scalability, providing new perspectives for future exploration in video latent representation and generation.
Authors: Hao Tang, Chengchao Shen
Abstract: Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial redundancy among vision tokens and shorten the length of vision token sequences for inference acceleration. Specifically, we propose a Spatial Token Fusion (STF) method to learn compact vision tokens for short vision token sequence, where spatial-adjacent tokens are fused into one. Meanwhile, weight-frozen vision encoder can not well adapt to the demand of extensive downstream vision-language tasks. To this end, we further introduce a Multi-Block Token Fusion (MBTF) module to supplement multi-granularity features for the reduced token sequence. Overall, we combine STF and MBTF module to balance token reduction and information preservation, thereby improving inference efficiency without sacrificing multimodal reasoning capabilities. Experimental results demonstrate that our method based on LLaVA-1.5 achieves comparable or even superior performance to the baseline on 8 popular vision-language benchmarks with only $25\%$ vision tokens of baseline. The source code and trained weights are available at https://github.com/visresearch/LLaVA-STF.
Authors: Van Nguyen Nguyen, Christian Forster, Sindi Shkodrani, Vincent Lepetit, Bugra Tekin, Cem Keskin, Tomas Hodan
Abstract: We introduce GoTrack, an efficient and accurate CAD-based method for 6DoF object pose refinement and tracking, which can handle diverse objects without any object-specific training. Unlike existing tracking methods that rely solely on an analysis-by-synthesis approach for model-to-frame registration, GoTrack additionally integrates frame-to-frame registration, which saves compute and stabilizes tracking. Both types of registration are realized by optical flow estimation. The model-to-frame registration is noticeably simpler than in existing methods, relying only on standard neural network blocks (a transformer is trained on top of DINOv2) and producing reliable pose confidence scores without a scoring network. For the frame-to-frame registration, which is an easier problem as consecutive video frames are typically nearly identical, we employ a light off-the-shelf optical flow model. We demonstrate that GoTrack can be seamlessly combined with existing coarse pose estimation methods to create a minimal pipeline that reaches state-of-the-art RGB-only results on standard benchmarks for 6DoF object pose estimation and tracking. Our source code and trained models are publicly available at https://github.com/facebookresearch/gotrack
Authors: Qiong Chang, Xinyuan Chen, Xiang Li, Weimin Wang, Jun Miyazaki
Abstract: The visual-based SLAM (Simultaneous Localization and Mapping) is a technology widely used in applications such as robotic navigation and virtual reality, which primarily focuses on detecting feature points from visual images to construct an unknown environmental map and simultaneously determines its own location. It usually imposes stringent requirements on hardware power consumption, processing speed and accuracy. Currently, the ORB (Oriented FAST and Rotated BRIEF)-based SLAM systems have exhibited superior performance in terms of processing speed and robustness. However, they still fall short of meeting the demands for real-time processing on mobile platforms. This limitation is primarily due to the time-consuming Oriented FAST calculations accounting for approximately half of the entire SLAM system. This paper presents two methods to accelerate the Oriented FAST feature detection on low-end embedded GPUs. These methods optimize the most time-consuming steps in Oriented FAST feature detection: FAST feature point detection and Harris corner detection, which is achieved by implementing a binary-level encoding strategy to determine candidate points quickly and a separable Harris detection strategy with efficient low-level GPU hardware-specific instructions. Extensive experiments on a Jetson TX2 embedded GPU demonstrate an average speedup of over 7.3 times compared to widely used OpenCV with GPU support. This significant improvement highlights its effectiveness and potential for real-time applications in mobile and resource-constrained environments.
Authors: Sangwon Jang, Taekyung Ki, Jaehyeong Jo, Jaehong Yoon, Soo Ye Kim, Zhe Lin, Sung Ju Hwang
Abstract: Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes increasingly impractical as model sizes continue to grow. In this work, we present Frame Guidance, a training-free guidance for controllable video generation based on frame-level signals, such as keyframes, style reference images, sketches, or depth maps. For practical training-free guidance, we propose a simple latent processing method that dramatically reduces memory usage, and apply a novel latent optimization strategy designed for globally coherent video generation. Frame Guidance enables effective control across diverse tasks, including keyframe guidance, stylization, and looping, without any training, compatible with any video models. Experimental results show that Frame Guidance can produce high-quality controlled videos for a wide range of tasks and input signals.
Authors: Ni Ding, Lei He, Shengbo Eben Li, Keqiang Li
Abstract: End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training flexibility, this paper proposes a hierarchical and decoupled post-training framework tailored for pretrained neural networks. By reconstructing intermediate feature maps from ground-truth labels, surrogate supervisory signals are introduced at transitional layers to enable independent training of specific components, thereby avoiding the complexity and coupling of conventional end-to-end backpropagation and providing interpretable insights into networks' internal mechanisms. To the best of our knowledge, this is the first method to formalize feature-level reverse computation as well-posed optimization problems, which we rigorously reformulate as systems of linear equations or least squares problems. This establishes a novel and efficient training paradigm that extends gradient backpropagation to feature backpropagation. Extensive experiments on multiple standard image classification benchmarks demonstrate that the proposed method achieves superior generalization performance and computational efficiency compared to traditional training approaches, validating its effectiveness and potential.
Authors: Mengya Xu, Zhongzhen Huang, Dillan Imans, Yiru Ye, Xiaofan Zhang, Qi Dou
Abstract: Effective evaluation is critical for driving advancements in MLLM research. The surgical action planning (SAP) task, which aims to generate future action sequences from visual inputs, demands precise and sophisticated analytical capabilities. Unlike mathematical reasoning, surgical decision-making operates in life-critical domains and requires meticulous, verifiable processes to ensure reliability and patient safety. This task demands the ability to distinguish between atomic visual actions and coordinate complex, long-horizon procedures, capabilities that are inadequately evaluated by current benchmarks. To address this gap, we introduce SAP-Bench, a large-scale, high-quality dataset designed to enable multimodal large language models (MLLMs) to perform interpretable surgical action planning. Our SAP-Bench benchmark, derived from the cholecystectomy procedures context with the mean duration of 1137.5s, and introduces temporally-grounded surgical action annotations, comprising the 1,226 clinically validated action clips (mean duration: 68.7s) capturing five fundamental surgical actions across 74 procedures. The dataset provides 1,152 strategically sampled current frames, each paired with the corresponding next action as multimodal analysis anchors. We propose the MLLM-SAP framework that leverages MLLMs to generate next action recommendations from the current surgical scene and natural language instructions, enhanced with injected surgical domain knowledge. To assess our dataset's effectiveness and the broader capabilities of current models, we evaluate seven state-of-the-art MLLMs (e.g., OpenAI-o1, GPT-4o, QwenVL2.5-72B, Claude-3.5-Sonnet, GeminiPro2.5, Step-1o, and GLM-4v) and reveal critical gaps in next action prediction performance.
Authors: Min-Jung Kim, Dongjin Kim, Seokju Yun, Jaegul Choo
Abstract: Video editing has garnered increasing attention alongside the rapid progress of diffusion-based video generation models. As part of these advancements, there is a growing demand for more accessible and controllable forms of video editing, such as prompt-based editing. Previous studies have primarily focused on tasks such as style transfer, background replacement, object substitution, and attribute modification, while maintaining the content structure of the source video. However, more complex tasks, including the addition of novel objects and nonrigid transformations, remain relatively unexplored. In this paper, we present TV-LiVE, a Training-free and text-guided Video editing framework via Layerinformed Vitality Exploitation. We empirically identify vital layers within the video generation model that significantly influence the quality of generated outputs. Notably, these layers are closely associated with Rotary Position Embeddings (RoPE). Based on this observation, our method enables both object addition and non-rigid video editing by selectively injecting key and value features from the source model into the corresponding layers of the target model guided by the layer vitality. For object addition, we further identify prominent layers to extract the mask regions corresponding to the newly added target prompt. We found that the extracted masks from the prominent layers faithfully indicate the region to be edited. Experimental results demonstrate that TV-LiVE outperforms existing approaches for both object addition and non-rigid video editing. Project Page: https://emjay73.github.io/TV_LiVE/
Authors: Zhiyuan Zhong, Zhen Sun, Yepang Liu, Xinlei He, Guanhong Tao
Abstract: Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of VLMs largely unexplored. Unlike prior work, we identify a novel attack surface that leverages cross-modal semantic mismatches as implicit triggers. Based on this insight, we propose BadSem (Backdoor Attack with Semantic Manipulation), a data poisoning attack that injects stealthy backdoors by deliberately misaligning image-text pairs during training. To perform the attack, we construct SIMBad, a dataset tailored for semantic manipulation involving color and object attributes. Extensive experiments across four widely used VLMs show that BadSem achieves over 98% average ASR, generalizes well to out-of-distribution datasets, and can transfer across poisoning modalities. Our detailed analysis using attention visualization shows that backdoored models focus on semantically sensitive regions under mismatched conditions while maintaining normal behavior on clean inputs. To mitigate the attack, we try two defense strategies based on system prompt and supervised fine-tuning but find that both of them fail to mitigate the semantic backdoor. Our findings highlight the urgent need to address semantic vulnerabilities in VLMs for their safer deployment.
Authors: Nada Aboudeshish, Dmitry Ignatov, Radu Timofte
Abstract: Data augmentation is a crucial technique in deep learning, particularly for tasks with limited dataset diversity, such as skeleton-based datasets. This paper proposes a comprehensive data augmentation framework that integrates geometric transformations, random cropping, rotation, zooming and intensity-based transformations, brightness and contrast adjustments to simulate real-world variations. Random cropping ensures the preservation of spatio-temporal integrity while addressing challenges such as viewpoint bias and occlusions. The augmentation pipeline generates three augmented versions for each sample in addition to the data set sample, thus quadrupling the data set size and enriching the diversity of gesture representations. The proposed augmentation strategy is evaluated on three models: multi-stream e2eET, FPPR point cloud-based hand gesture recognition (HGR), and DD-Network. Experiments are conducted on benchmark datasets including DHG14/28, SHREC'17, and JHMDB. The e2eET model, recognized as the state-of-the-art for hand gesture recognition on DHG14/28 and SHREC'17. The FPPR-PCD model, the second-best performing model on SHREC'17, excels in point cloud-based gesture recognition. DD-Net, a lightweight and efficient architecture for skeleton-based action recognition, is evaluated on SHREC'17 and the Human Motion Data Base (JHMDB). The results underline the effectiveness and versatility of the proposed augmentation strategy, significantly improving model generalization and robustness across diverse datasets and architectures. This framework not only establishes state-of-the-art results on all three evaluated models but also offers a scalable solution to advance HGR and action recognition applications in real-world scenarios. The framework is available at https://github.com/NadaAbodeshish/Random-Cropping-augmentation-HGR
URLs: https://github.com/NadaAbodeshish/Random-Cropping-augmentation-HGR
Authors: Tianyi Bai, Yuxuan Fan, Jiantao Qiu, Fupeng Sun, Jiayi Song, Junlin Han, Zichen Liu, Conghui He, Wentao Zhang, Binhang Yuan
Abstract: Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks but still struggle with fine-grained visual differences, leading to hallucinations or missed semantic shifts. We attribute this to limitations in both training data and learning objectives. To address these issues, we propose a controlled data generation pipeline that produces minimally edited image pairs with semantically aligned captions. Using this pipeline, we construct the Micro Edit Dataset (MED), containing over 50K image-text pairs spanning 11 fine-grained edit categories, including attribute, count, position, and object presence changes. Building on MED, we introduce a supervised fine-tuning (SFT) framework with a feature-level consistency loss that promotes stable visual embeddings under small edits. We evaluate our approach on the Micro Edit Detection benchmark, which includes carefully balanced evaluation pairs designed to test sensitivity to subtle visual variations across the same edit categories. Our method improves difference detection accuracy and reduces hallucinations compared to strong baselines, including GPT-4o. Moreover, it yields consistent gains on standard vision-language tasks such as image captioning and visual question answering. These results demonstrate the effectiveness of combining targeted data and alignment objectives for enhancing fine-grained visual reasoning in MLLMs.
Authors: Tianyi Bai, Zengjie Hu, Fupeng Sun, Jiantao Qiu, Yizhen Jiang, Guangxin He, Bohan Zeng, Conghui He, Binhang Yuan, Wentao Zhang
Abstract: Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific analysis. However, most MLLMs adopt a static inference paradigm, encoding the entire image into fixed visual tokens upfront, which limits their ability to iteratively refine understanding or adapt to context during inference. This contrasts sharply with human perception, which is dynamic, selective, and feedback-driven. In this work, we introduce a novel framework for inference-time visual token scaling that enables MLLMs to perform iterative, verifier-guided reasoning over visual content. We formulate the problem as a Markov Decision Process, involving a reasoner that proposes visual actions and a verifier, which is trained via multi-step Direct Preference Optimization (DPO), that evaluates these actions and determines when reasoning should terminate. To support this, we present a new dataset, VTS, comprising supervised reasoning trajectories (VTS-SFT) and preference-labeled reasoning comparisons (VTS-DPO). Our method significantly outperforms existing approaches across diverse visual reasoning benchmarks, offering not only improved accuracy but also more interpretable and grounded reasoning processes. These results demonstrate the promise of dynamic inference mechanisms for enabling fine-grained, context-aware visual reasoning in next-generation MLLMs.
Authors: Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi, Paolo Favaro
Abstract: Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere video generation. We argue that the training dynamics of VDMs, driven by the need to model coherent sequences, naturally pushes them to internalize structured representations and an implicit understanding of the visual world. To probe the extent of this internal knowledge, we introduce a few-shot fine-tuning framework that repurposes VDMs for new tasks using only a handful of examples. Our method transforms each task into a visual transition, enabling the training of LoRA weights on short input-output sequences without altering the generative interface of a frozen VDM. Despite minimal supervision, the model exhibits strong generalization across diverse tasks, from low-level vision (for example, segmentation and pose estimation) to high-level reasoning (for example, on ARC-AGI). These results reframe VDMs as more than generative engines. They are adaptable visual learners with the potential to serve as the backbone for future foundation models in vision.
Authors: Aditya Chakravarty
Abstract: Diffusion models have shown remarkable flexibility for solving inverse problems without task-specific retraining. However, existing approaches such as Manifold Preserving Guided Diffusion (MPGD) apply only a single gradient update per denoising step, limiting restoration fidelity and robustness, especially in embedded or out-of-distribution settings. In this work, we introduce a multistep optimization strategy within each denoising timestep, significantly enhancing image quality, perceptual accuracy, and generalization. Our experiments on super-resolution and Gaussian deblurring demonstrate that increasing the number of gradient updates per step improves LPIPS and PSNR with minimal latency overhead. Notably, we validate this approach on a Jetson Orin Nano using degraded ImageNet and a UAV dataset, showing that MPGD, originally trained on face datasets, generalizes effectively to natural and aerial scenes. Our findings highlight MPGD's potential as a lightweight, plug-and-play restoration module for real-time visual perception in embodied AI agents such as drones and mobile robots.
Authors: Kavitha Viswanathan, Vrinda Goel, Shlesh Gholap, Devayan Ghosh, Madhav Gupta, Dhruvi Ganatra, Sanket Potdar, Amit Sethi
Abstract: Real-world surveillance often renders faces and license plates unrecognizable in individual low-resolution (LR) frames, hindering reliable identification. To advance temporal recognition models, we present FANVID, a novel video-based benchmark comprising nearly 1,463 LR clips (180 x 320, 20--60 FPS) featuring 63 identities and 49 license plates from three English-speaking countries. Each video includes distractor faces and plates, increasing task difficulty and realism. The dataset contains 31,096 manually verified bounding boxes and labels. FANVID defines two tasks: (1) face matching -- detecting LR faces and matching them to high-resolution mugshots, and (2) license plate recognition -- extracting text from LR plates without a predefined database. Videos are downsampled from high-resolution sources to ensure that faces and text are indecipherable in single frames, requiring models to exploit temporal information. We introduce evaluation metrics adapted from mean Average Precision at IoU > 0.5, prioritizing identity correctness for faces and character-level accuracy for text. A baseline method with pre-trained video super-resolution, detection, and recognition achieved performance scores of 0.58 (face matching) and 0.42 (plate recognition), highlighting both the feasibility and challenge of the tasks. FANVID's selection of faces and plates balances diversity with recognition challenge. We release the software for data access, evaluation, baseline, and annotation to support reproducibility and extension. FANVID aims to catalyze innovation in temporal modeling for LR recognition, with applications in surveillance, forensics, and autonomous vehicles.
Authors: Adam W. Harley, Yang You, Xinglong Sun, Yang Zheng, Nikhil Raghuraman, Yunqi Gu, Sheldon Liang, Wen-Hsuan Chu, Achal Dave, Pavel Tokmakov, Suya You, Rares Ambrus, Katerina Fragkiadaki, Leonidas J. Guibas
Abstract: We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers high-resolution and dense (all-pixel) correspondence fields, which can be visualized as flow maps. Unlike existing optical flow methods, our approach corresponds one frame to hundreds of subsequent frames, rather than just the next frame. We develop a new architecture for this task, blending techniques from existing work in optical flow and point tracking: the model performs iterative inference on low-resolution grids of correspondence estimates, propagating information spatially via 2D convolution layers, and propagating information temporally via pixel-aligned attention layers. The model is fast and parameter-efficient (16 million parameters), and delivers state-of-the-art point tracking accuracy at high resolution (i.e., tracking 768x1024 pixels, on a 40G GPU). A benefit of our design is that we can train on a wider set of datasets, and we find that doing so is crucial for top performance. We provide an extensive ablation study on our architecture details and training recipe, making it clear which details matter most. Our code and model weights are available at https://alltracker.github.io .
Authors: Dane Williamson, Yangfeng Ji, Matthew Dwyer
Abstract: Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility can obscure critical limitations. In this work, we propose a diagnostic test for class sensitivity: a method's ability to distinguish between competing class labels on the same input. Through extensive experiments, we show that many widely used saliency methods produce nearly identical explanations regardless of the class label, calling into question their reliability. We find that class-insensitive behavior persists across architectures and datasets, suggesting the failure mode is structural rather than model-specific. Motivated by these findings, we introduce CASE, a contrastive explanation method that isolates features uniquely discriminative for the predicted class. We evaluate CASE using the proposed diagnostic and a perturbation-based fidelity test, and show that it produces faithful and more class-specific explanations than existing methods.
Authors: Yijie Deng, Shuaihang Yuan, Geeta Chandra Raju Bethala, Anthony Tzes, Yu-Shen Liu, Yi Fang
Abstract: Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint. While recent methods leverage powerful novel view synthesis (NVS) techniques, such as three-dimensional Gaussian splatting (3DGS), they typically rely on randomly sampling multiple viewpoints or trajectories to ensure comprehensive coverage of discriminative visual cues. This approach, however, creates significant redundancy through overlapping image samples and lacks principled view selection, substantially increasing both rendering and comparison overhead. In this paper, we introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching. Our approach integrates cross-level semantic scoring, utilizing CLIP-derived relevancy fields to identify regions with high semantic similarity to the target object class, with fine-grained local geometric scoring that performs precise pose estimation within promising regions. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on simulated IIN benchmarks and real-world applicability.
Authors: Satvik Praveen, Yoonsung Jung
Abstract: Object detection is vital in precision agriculture for plant monitoring, disease detection, and yield estimation. However, models like YOLO struggle with occlusions, irregular structures, and background noise, reducing detection accuracy. While Spatial Transformer Networks (STNs) improve spatial invariance through learned transformations, affine mappings are insufficient for non-rigid deformations such as bent leaves and overlaps. We propose CBAM-STN-TPS-YOLO, a model integrating Thin-Plate Splines (TPS) into STNs for flexible, non-rigid spatial transformations that better align features. Performance is further enhanced by the Convolutional Block Attention Module (CBAM), which suppresses background noise and emphasizes relevant spatial and channel-wise features. On the occlusion-heavy Plant Growth and Phenotyping (PGP) dataset, our model outperforms STN-YOLO in precision, recall, and mAP. It achieves a 12% reduction in false positives, highlighting the benefits of improved spatial flexibility and attention-guided refinement. We also examine the impact of the TPS regularization parameter in balancing transformation smoothness and detection performance. This lightweight model improves spatial awareness and supports real-time edge deployment, making it ideal for smart farming applications requiring accurate and efficient monitoring.
Authors: Chengchao Shen, Dawei Liu, Jianxin Wang
Abstract: Contrastive learning for single object centric images has achieved remarkable progress on unsupervised representation, but suffering inferior performance on the widespread images with multiple objects. In this paper, we propose a simple but effective method, Multiple Object Stitching (MOS), to refine the unsupervised representation for multi-object images. Specifically, we construct the multi-object images by stitching the single object centric ones, where the objects in the synthesized multi-object images are predetermined. Hence, compared to the existing contrastive methods, our method provides additional object correspondences between multi-object images without human annotations. In this manner, our method pays more attention to the representations of each object in multi-object image, thus providing more detailed representations for complicated downstream tasks, such as object detection and semantic segmentation. Experimental results on ImageNet, CIFAR and COCO datasets demonstrate that our proposed method achieves the leading unsupervised representation performance on both single object centric images and multi-object ones. The source code is available at https://github.com/visresearch/MultipleObjectStitching.
URLs: https://github.com/visresearch/MultipleObjectStitching.
Authors: Jiaying He, Yitong Lin, Jiahe Chen, Honghui Xu, Jianwei Zheng
Abstract: For the immanent challenge of insufficiently annotated samples in the medical field, semi-supervised medical image segmentation (SSMIS) offers a promising solution. Despite achieving impressive results in delineating primary target areas, most current methodologies struggle to precisely capture the subtle details of boundaries. This deficiency often leads to significant diagnostic inaccuracies. To tackle this issue, we introduce C3S3, a novel semi-supervised segmentation model that synergistically integrates complementary competition and contrastive selection. This design significantly sharpens boundary delineation and enhances overall precision. Specifically, we develop an $\textit{Outcome-Driven Contrastive Learning}$ module dedicated to refining boundary localization. Additionally, we incorporate a $\textit{Dynamic Complementary Competition}$ module that leverages two high-performing sub-networks to generate pseudo-labels, thereby further improving segmentation quality. The proposed C3S3 undergoes rigorous validation on two publicly accessible datasets, encompassing the practices of both MRI and CT scans. The results demonstrate that our method achieves superior performance compared to previous cutting-edge competitors. Especially, on the 95HD and ASD metrics, our approach achieves a notable improvement of at least $6\%$, highlighting the significant advancements. The code is available at https://github.com/Y-TARL/C3S3.
Authors: Bolin Chen, Shanzhi Yin, Goluck Konuko, Giuseppe Valenzise, Zihan Zhang, Shiqi Wang, Yan Ye
Abstract: The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware representation and lifelike synthesis. Generative Face Video Coding (GFVC) stands at the forefront of this revolution, which could characterize complex facial dynamics into compact latent codes for bitstream compactness at the encoder side and leverages powerful deep generative models to reconstruct high-fidelity face signal from the compressed latent codes at the decoder side. As such, this well-designed GFVC paradigm could enable high-fidelity face video communication at ultra-low bitrate ranges, far surpassing the capabilities of the latest Versatile Video Coding (VVC) standard. To pioneer foundational research and accelerate the evolution of GFVC, this paper presents the first comprehensive survey of GFVC technologies, systematically bridging critical gaps between theoretical innovation and industrial standardization. In particular, we first review a broad range of existing GFVC methods with different feature representations and optimization strategies, and conduct a thorough benchmarking analysis. In addition, we construct a large-scale GFVC-compressed face video database with subjective Mean Opinion Scores (MOSs) based on human perception, aiming to identify the most appropriate quality metrics tailored to GFVC. Moreover, we summarize the GFVC standardization potentials with a unified high-level syntax and develop a low-complexity GFVC system which are both expected to push forward future practical deployments and applications. Finally, we envision the potential of GFVC in industrial applications and deliberate on the current challenges and future opportunities.
Authors: Ruchit Rawal, Reza Shirkavand, Heng Huang, Gowthami Somepalli, Tom Goldstein
Abstract: Video large language models have not yet been widely deployed, largely due to their tendency to hallucinate. Typical benchmarks for Video-LLMs rely simply on multiple-choice questions. Unfortunately, VideoLLMs hallucinate far more aggressively on freeform text generation tasks like video captioning than they do on multiple choice verification tasks. To address this weakness, we propose ARGUS, a VideoLLM benchmark that measures freeform video captioning performance. By comparing VideoLLM outputs to human ground truth captions, ARGUS quantifies dual metrics. First, we measure the rate of hallucinations in the form of incorrect statements about video content or temporal relationships. Second, we measure the rate at which the model omits important descriptive details. Together, these dual metrics form a comprehensive view of video captioning performance.
Authors: Xunjie He, Christina Dao Wen Lee, Meiling Wang, Chengran Yuan, Zefan Huang, Yufeng Yue, Marcelo H. Ang Jr
Abstract: Collaborative perception plays a crucial role in enhancing environmental understanding by expanding the perceptual range and improving robustness against sensor failures, which primarily involves collaborative 3D detection and tracking tasks. The former focuses on object recognition in individual frames, while the latter captures continuous instance tracklets over time. However, existing works in both areas predominantly focus on the vehicle superclass, lacking effective solutions for both multi-class collaborative detection and tracking. This limitation hinders their applicability in real-world scenarios, which involve diverse object classes with varying appearances and motion patterns. To overcome these limitations, we propose a multi-class collaborative detection and tracking framework tailored for diverse road users. We first present a detector with a global spatial attention fusion (GSAF) module, enhancing multi-scale feature learning for objects of varying sizes. Next, we introduce a tracklet RE-IDentification (REID) module that leverages visual semantics with a vision foundation model to effectively reduce ID SWitch (IDSW) errors, in cases of erroneous mismatches involving small objects like pedestrians. We further design a velocity-based adaptive tracklet management (VATM) module that adjusts the tracking interval dynamically based on object motion. Extensive experiments on the V2X-Real and OPV2V datasets show that our approach significantly outperforms existing state-of-the-art methods in both detection and tracking accuracy.
Authors: Jintao Tong, Ran Ma, Yixiong Zou, Guangyao Chen, Yuhua Li, Ruixuan Li
Abstract: Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few samples are available for efficient fine-tuning. There are majorly two challenges in this task: (1) the domain gap and (2) fine-tuning with scarce data. To solve these challenges, we revisit the adapter-based methods, and discover an intriguing insight not explored in previous works: the adapter not only helps the fine-tuning of downstream tasks but also naturally serves as a domain information decoupler. Then, we delve into this finding for an interpretation, and find the model's inherent structure could lead to a natural decoupling of domain information. Building upon this insight, we propose the Domain Feature Navigator (DFN), which is a structure-based decoupler instead of loss-based ones like current works, to capture domain-specific information, thereby directing the model's attention towards domain-agnostic knowledge. Moreover, to prevent the potential excessive overfitting of DFN during the source-domain training, we further design the SAM-SVN method to constrain DFN from learning sample-specific knowledge. On target domains, we freeze the model and fine-tune the DFN to learn target-specific knowledge specific. Extensive experiments demonstrate that our method surpasses the state-of-the-art method in CD-FSS significantly by 2.69% and 4.68% MIoU in 1-shot and 5-shot scenarios, respectively.
Authors: Peiru Yang, Jinhua Yin, Haoran Zheng, Xueying Bai, Huili Wang, Yufei Sun, Xintian Li, Shangguang Wang, Yongfeng Huang, Tao Qi
Abstract: Multimodal retrieval-augmented generation (RAG) systems enhance large vision-language models by integrating cross-modal knowledge, enabling their increasing adoption across real-world multimodal tasks. These knowledge databases may contain sensitive information that requires privacy protection. However, multimodal RAG systems inherently grant external users indirect access to such data, making them potentially vulnerable to privacy attacks, particularly membership inference attacks (MIAs). % Existing MIA methods targeting RAG systems predominantly focus on the textual modality, while the visual modality remains relatively underexplored. To bridge this gap, we propose MrM, the first black-box MIA framework targeted at multimodal RAG systems. It utilizes a multi-object data perturbation framework constrained by counterfactual attacks, which can concurrently induce the RAG systems to retrieve the target data and generate information that leaks the membership information. Our method first employs an object-aware data perturbation method to constrain the perturbation to key semantics and ensure successful retrieval. Building on this, we design a counterfact-informed mask selection strategy to prioritize the most informative masked regions, aiming to eliminate the interference of model self-knowledge and amplify attack efficacy. Finally, we perform statistical membership inference by modeling query trials to extract features that reflect the reconstruction of masked semantics from response patterns. Experiments on two visual datasets and eight mainstream commercial visual-language models (e.g., GPT-4o, Gemini-2) demonstrate that MrM achieves consistently strong performance across both sample-level and set-level evaluations, and remains robust under adaptive defenses.
Authors: Changsheng Gao, Wei Zhou, Guosheng Lin, Weisi Lin
Abstract: The widespread deployment of large models in resource-constrained environments has underscored the need for efficient transmission of intermediate feature representations. In this context, feature coding, which compresses features into compact bitstreams, becomes a critical component for scenarios involving feature transmission, storage, and reuse. However, this compression process introduces inherent semantic degradation that is notoriously difficult to quantify with traditional metrics. To address this, this paper introduces the research problem of Compressed Feature Quality Assessment (CFQA), which seeks to evaluate the semantic fidelity of compressed features. To advance CFQA research, we propose the first benchmark dataset, comprising 300 original features and 12000 compressed features derived from three vision tasks and four feature codecs. Task-specific performance drops are provided as true semantic distortion for the evaluation of CFQA metrics. We assess the performance of three widely used metrics (MSE, cosine similarity, and Centered Kernel Alignment) in capturing semantic degradation. The results underscore the representativeness of the dataset and highlight the need for more refined metrics capable of addressing the nuances of semantic distortion in compressed features. To facilitate the ongoing development of CFQA research, we release the dataset and all accompanying source code at \href{https://github.com/chansongoal/Compressed-Feature-Quality-Assessment}{https://github.com/chansongoal/Compressed-Feature-Quality-Assessment}. This contribution aims to advance the field and provide a foundational resource for the community to explore CFQA.
URLs: https://github.com/chansongoal/Compressed-Feature-Quality-Assessment, https://github.com/chansongoal/Compressed-Feature-Quality-Assessment
Authors: Sheng-Kai Huang, Jiun-Feng Chang, Chun-Rong Huang
Abstract: In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different tasks. In order to solve the aforementioned problems, we propose a novel dynamic prompt transformer (DPFormer) with prompt schemes. The prompt schemes help the DPFormer memorize learned knowledge of previous classes and tasks, and keep on learning new knowledge from new classes and tasks under a single network structure with a nearly fixed number of model parameters. Moreover, they also provide discrepant information to represent different tasks to solve the inter-task confusion problem. Based on prompt schemes, a unified classification module with the binary cross entropy loss, the knowledge distillation loss and the auxiliary loss is proposed to train the whole model in an end-to-end trainable manner. Compared with state-of-the-art methods, our method achieves the best performance in the CIFAR-100, ImageNet100 and ImageNet1K datasets under different class-incremental settings in continual learning. The source code will be available at our GitHub after acceptance.
Authors: Jie He, Minglang Chen, Minying Lu, Bocheng Liang, Junming Wei, Guiyan Peng, Jiaxi Chen, Ying Tan
Abstract: Accurate ultrasound image segmentation is a prerequisite for precise biometrics and accurate assessment. Relying on manual delineation introduces significant errors and is time-consuming. However, existing segmentation models are designed based on objects in natural scenes, making them difficult to adapt to ultrasound objects with high noise and high similarity. This is particularly evident in small object segmentation, where a pronounced jagged effect occurs. Therefore, this paper proposes a fetal femur and cranial ultrasound image segmentation model based on feature perception and Mamba enhancement to address these challenges. Specifically, a longitudinal and transverse independent viewpoint scanning convolution block and a feature perception module were designed to enhance the ability to capture local detail information and improve the fusion of contextual information. Combined with the Mamba-optimized residual structure, this design suppresses the interference of raw noise and enhances local multi-dimensional scanning. The system builds global information and local feature dependencies, and is trained with a combination of different optimizers to achieve the optimal solution. After extensive experimental validation, the FAMSeg network achieved the fastest loss reduction and the best segmentation performance across images of varying sizes and orientations.
Authors: Nishi Chaudhary, S M Jamil Uddin, Sathvik Sharath Chandra, Anto Ovid, Alex Albert
Abstract: The recent emergence of multimodal large language models (LLMs) has introduced new opportunities for improving visual hazard recognition on construction sites. Unlike traditional computer vision models that rely on domain-specific training and extensive datasets, modern LLMs can interpret and describe complex visual scenes using simple natural language prompts. However, despite growing interest in their applications, there has been limited investigation into how different LLMs perform in safety-critical visual tasks within the construction domain. To address this gap, this study conducts a comparative evaluation of five state-of-the-art LLMs: Claude-3 Opus, GPT-4.5, GPT-4o, GPT-o3, and Gemini 2.0 Pro, to assess their ability to identify potential hazards from real-world construction images. Each model was tested under three prompting strategies: zero-shot, few-shot, and chain-of-thought (CoT). Zero-shot prompting involved minimal instruction, few-shot incorporated basic safety context and a hazard source mnemonic, and CoT provided step-by-step reasoning examples to scaffold model thinking. Quantitative analysis was performed using precision, recall, and F1-score metrics across all conditions. Results reveal that prompting strategy significantly influenced performance, with CoT prompting consistently producing higher accuracy across models. Additionally, LLM performance varied under different conditions, with GPT-4.5 and GPT-o3 outperforming others in most settings. The findings also demonstrate the critical role of prompt design in enhancing the accuracy and consistency of multimodal LLMs for construction safety applications. This study offers actionable insights into the integration of prompt engineering and LLMs for practical hazard recognition, contributing to the development of more reliable AI-assisted safety systems.
Authors: Wei Yao, Yunlian Sun, Chang Liu, Hongwen Zhang, Jinhui Tang
Abstract: Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realistic human motions has become a promising research direction. However, existing motion-capture techniques and generative models often neglect physical constraints, leading to artifacts such as interpenetration, sliding, and floating. These issues are exacerbated in multi-person motion generation, where complex interactions are involved. To address these limitations, we introduce physical mapping, integrated throughout the human interaction generation pipeline. Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space. The resulting motions are adjusted to adhere to real-world physics constraints while retaining their original semantic meaning. This mapping not only improves MoCap data quality but also directly informs post-processing of generated motions. Given the unique interactivity of multi-person scenarios, we propose a tailored motion representation framework. Motion Consistency (MC) and Marker-based Interaction (MI) loss functions are introduced to improve model performance. Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity. Project page http://yw0208.github.io/physiinter
Authors: Taeryung Lee, Hyeongjin Nam, Gyeongsik Moon, Kyoung Mu Lee
Abstract: Sign language generation (SLG), or text-to-sign generation, bridges the gap between signers and non-signers. Despite recent progress in SLG, existing methods still often suffer from incorrect lexical ordering and low semantic accuracy. This is primarily due to sentence-level condition, which encodes the entire sentence of the input text into a single feature vector as a condition for SLG. This approach fails to capture the temporal structure of sign language and lacks the granularity of word-level semantics, often leading to disordered sign sequences and ambiguous motions. To overcome these limitations, we propose GLOS, a sign language generation framework with temporally aligned gloss-level conditioning. First, we employ gloss-level conditions, which we define as sequences of gloss embeddings temporally aligned with the motion sequence. This enables the model to access both the temporal structure of sign language and word-level semantics at each timestep. As a result, this allows for fine-grained control of signs and better preservation of lexical order. Second, we introduce a condition fusion module, temporal alignment conditioning (TAC), to efficiently deliver the word-level semantic and temporal structure provided by the gloss-level condition to the corresponding motion timesteps. Our method, which is composed of gloss-level conditions and TAC, generates signs with correct lexical order and high semantic accuracy, outperforming prior methods on CSL-Daily and Phoenix-2014T.
Authors: Jinyoung Park, Jeehye Na, Jinyoung Kim, Hyunwoo J. Kim
Abstract: Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training in enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown impressive success by employing a PPO-style reinforcement algorithm with group-based normalized rewards. However, the application of GRPO to Video Large Language Models (Video LLMs) has been less studied. In this paper, we explore GRPO for video LLMs and identify two primary issues that impede its effective learning: (1) reliance on safeguards, and (2) the vanishing advantage problem. To mitigate these challenges, we propose DeepVideo-R1, a video large language model trained with our proposed Reg-GRPO (Regressive GRPO) and difficulty-aware data augmentation strategy. Reg-GRPO reformulates the GRPO objective as a regression task, directly predicting the advantage in GRPO. This design eliminates the need for safeguards like clipping and min functions, thereby facilitating more direct policy guidance by aligning the model with the advantage values. We also design the difficulty-aware data augmentation strategy that dynamically augments training samples at solvable difficulty levels, fostering diverse and informative reward signals. Our comprehensive experiments show that DeepVideo-R1 significantly improves video reasoning performance across multiple video reasoning benchmarks.
Authors: CH Cho, WJ Moon, W Jun, MS Jung, JP Heo
Abstract: Partially Relevant Video Retrieval~(PRVR) aims to retrieve a video where a specific segment is relevant to a given text query. Typical training processes of PRVR assume a one-to-one relationship where each text query is relevant to only one video. However, we point out the inherent ambiguity between text and video content based on their conceptual scope and propose a framework that incorporates this ambiguity into the model learning process. Specifically, we propose Ambiguity-Restrained representation Learning~(ARL) to address ambiguous text-video pairs. Initially, ARL detects ambiguous pairs based on two criteria: uncertainty and similarity. Uncertainty represents whether instances include commonly shared context across the dataset, while similarity indicates pair-wise semantic overlap. Then, with the detected ambiguous pairs, our ARL hierarchically learns the semantic relationship via multi-positive contrastive learning and dual triplet margin loss. Additionally, we delve into fine-grained relationships within the video instances. Unlike typical training at the text-video level, where pairwise information is provided, we address the inherent ambiguity within frames of the same untrimmed video, which often contains multiple contexts. This allows us to further enhance learning at the text-frame level. Lastly, we propose cross-model ambiguity detection to mitigate the error propagation that occurs when a single model is employed to detect ambiguous pairs for its training. With all components combined, our proposed method demonstrates its effectiveness in PRVR.
Authors: Dasol Hong, Wooju Lee, Hyun Myung
Abstract: Prompt tuning, which adapts vision-language models by freezing model parameters and optimizing only the prompt, has proven effective for task-specific adaptations. The core challenge in prompt tuning is improving specialization for a specific task and generalization for unseen domains. However, frozen encoders often produce misaligned features, leading to confusion between classes and limiting specialization. To overcome this issue, we propose a confusion-aware loss (CoA-loss) that improves specialization by refining the decision boundaries between confusing classes. Additionally, we mathematically demonstrate that a mixture model can enhance generalization without compromising specialization. This is achieved using confidence-aware weights (CoA-weights), which adjust the weights of each prediction in the mixture model based on its confidence within the class domains. Extensive experiments show that CoCoA-Mix, a mixture model with CoA-loss and CoA-weights, outperforms state-of-the-art methods by enhancing specialization and generalization. Our code is publicly available at https://github.com/url-kaist/CoCoA-Mix.
Authors: Yahao Shi, Yang Liu, Yanmin Wu, Xing Liu, Chen Zhao, Jie Luo, Bin Zhou
Abstract: We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to rasterization-based engines, while skeletal methods demand significant manual effort and lack cross-category generalization. Animating existing 3D assets, instead of creating 4D assets from scratch, demands a deep understanding of the input's 3D structure. To tackle these challenges, we present a 4D diffusion model that denoises sequences of latent sets, which are then decoded to produce mesh animations from point cloud trajectory sequences. These latent sets leverage a transformer-based variational autoencoder, simultaneously capturing 3D shape and motion information. By employing a spatiotemporal, transformer-based diffusion model, information is exchanged across multiple latent frames, enhancing the efficiency and generalization of the generated results. Our experimental results demonstrate that DriveAnyMesh can rapidly produce high-quality animations for complex motions and is compatible with modern rendering engines. This method holds potential for applications in both the gaming and filming industries.
Authors: Yongsen Mao, Junhao Zhong, Chuan Fang, Jia Zheng, Rui Tang, Hao Zhu, Ping Tan, Zihan Zhou
Abstract: SpatialLM is a large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object boxes with their semantic categories. Unlike previous methods which exploit task-specific network designs, our model adheres to the standard multimodal LLM architecture and is fine-tuned directly from open-source LLMs. To train SpatialLM, we collect a large-scale, high-quality synthetic dataset consisting of the point clouds of 12,328 indoor scenes (54,778 rooms) with ground-truth 3D annotations, and conduct a careful study on various modeling and training decisions. On public benchmarks, our model gives state-of-the-art performance in layout estimation and competitive results in 3D object detection. With that, we show a feasible path for enhancing the spatial understanding capabilities of modern LLMs for applications in augmented reality, embodied robotics, and more.
Authors: Xiangyu Guo, Zhanqian Wu, Kaixin Xiong, Ziyang Xu, Lijun Zhou, Gangwei Xu, Shaoqing Xu, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang
Abstract: We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-language models that provides scene-level and instance-level supervision. Extensive experiments on the nuScenes benchmark demonstrate that Genesis achieves state-of-the-art performance across video and LiDAR metrics (FVD 16.95, FID 4.24, Chamfer 0.611), and benefits downstream tasks including segmentation and 3D detection, validating the semantic fidelity and practical utility of the generated data.
Authors: Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, Jianzong Wang
Abstract: One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization methods cannot take both effectiveness and efficiency into account. In this paper, we propose MoQAE, a novel mixed-precision quantization method via mixture of quantization-aware experts. First, we view different quantization bit-width configurations as experts and use the traditional mixture of experts (MoE) method to select the optimal configuration. To avoid the inefficiency caused by inputting tokens one by one into the router in the traditional MoE method, we input the tokens into the router chunk by chunk. Second, we design a lightweight router-only fine-tuning process to train MoQAE with a comprehensive loss to learn the trade-off between model accuracy and memory usage. Finally, we introduce a routing freezing (RF) and a routing sharing (RS) mechanism to further reduce the inference overhead. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art KV cache quantization approaches in both efficiency and effectiveness.
Authors: Xiaomeng Zhu, Jacob Henningsson, Duruo Li, P\"ar M{\aa}rtensson, Lars Hanson, M{\aa}rten Bj\"orkman, Atsuto Maki
Abstract: This paper addresses key aspects of domain randomization in generating synthetic data for manufacturing object detection applications. To this end, we present a comprehensive data generation pipeline that reflects different factors: object characteristics, background, illumination, camera settings, and post-processing. We also introduce the Synthetic Industrial Parts Object Detection dataset (SIP15-OD) consisting of 15 objects from three industrial use cases under varying environments as a test bed for the study, while also employing an industrial dataset publicly available for robotic applications. In our experiments, we present more abundant results and insights into the feasibility as well as challenges of sim-to-real object detection. In particular, we identified material properties, rendering methods, post-processing, and distractors as important factors. Our method, leveraging these, achieves top performance on the public dataset with Yolov8 models trained exclusively on synthetic data; mAP@50 scores of 96.4% for the robotics dataset, and 94.1%, 99.5%, and 95.3% across three of the SIP15-OD use cases, respectively. The results showcase the effectiveness of the proposed domain randomization, potentially covering the distribution close to real data for the applications.
Authors: Bowen Liu, Weiyi Zhang, Peranut Chotcomwongse, Xiaolan Chen, Ruoyu Chen, Pawin Pakaymaskul, Niracha Arjkongharn, Nattaporn Vongsa, Xuelian Cheng, Zongyuan Ge, Kun Huang, Xiaohui Li, Yiru Duan, Zhenbang Wang, BaoYe Xie, Qiang Chen, Huazhu Fu, Michael A. Mahr, Jiaqi Qu, Wangyiyang Chen, Shiye Wang, Yubo Tan, Yongjie Li, Mingguang He, Danli Shi, Paisan Ruamviboonsuk
Abstract: Optical Coherence Tomography (OCT) provides high-resolution, 3D, and non-invasive visualization of retinal layers in vivo, serving as a critical tool for lesion localization and disease diagnosis. However, its widespread adoption is limited by equipment costs and the need for specialized operators. In comparison, 2D color fundus photography offers faster acquisition and greater accessibility with less dependence on expensive devices. Although generative artificial intelligence has demonstrated promising results in medical image synthesis, translating 2D fundus images into 3D OCT images presents unique challenges due to inherent differences in data dimensionality and biological information between modalities. To advance generative models in the fundus-to-3D-OCT setting, the Asia Pacific Tele-Ophthalmology Society (APTOS-2024) organized a challenge titled Artificial Intelligence-based OCT Generation from Fundus Images. This paper details the challenge framework (referred to as APTOS-2024 Challenge), including: the benchmark dataset, evaluation methodology featuring two fidelity metrics-image-based distance (pixel-level OCT B-scan similarity) and video-based distance (semantic-level volumetric consistency), and analysis of top-performing solutions. The challenge attracted 342 participating teams, with 42 preliminary submissions and 9 finalists. Leading methodologies incorporated innovations in hybrid data preprocessing or augmentation (cross-modality collaborative paradigms), pre-training on external ophthalmic imaging datasets, integration of vision foundation models, and model architecture improvement. The APTOS-2024 Challenge is the first benchmark demonstrating the feasibility of fundus-to-3D-OCT synthesis as a potential solution for improving ophthalmic care accessibility in under-resourced healthcare settings, while helping to expedite medical research and clinical applications.
Authors: Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
Abstract: Generating high fidelity, differentially private (DP) synthetic images offers a promising route to share and analyze sensitive visual data without compromising individual privacy. However, existing DP image synthesis methods struggle to produce high resolution outputs that faithfully capture the structure of the original data. In this paper, we introduce a novel method, referred to as Synthesis via Private Textual Intermediaries (SPTI), that can generate high resolution DP images with easy adoption. The key idea is to shift the challenge of DP image synthesis from the image domain to the text domain by leveraging state of the art DP text generation methods. SPTI first summarizes each private image into a concise textual description using image to text models, then applies a modified Private Evolution algorithm to generate DP text, and finally reconstructs images using text to image models. Notably, SPTI requires no model training, only inference with off the shelf models. Given a private dataset, SPTI produces synthetic images of substantially higher quality than prior DP approaches. On the LSUN Bedroom dataset, SPTI attains an FID less than or equal to 26.71 under epsilon equal to 1.0, improving over Private Evolution FID of 40.36. Similarly, on MM CelebA HQ, SPTI achieves an FID less than or equal to 33.27 at epsilon equal to 1.0, compared to 57.01 from DP fine tuning baselines. Overall, our results demonstrate that Synthesis via Private Textual Intermediaries provides a resource efficient and proprietary model compatible framework for generating high resolution DP synthetic images, greatly expanding access to private visual datasets.
Authors: Hao Yang, JianYu Wu, Run Fang, Xuelian Zhao, Yuan Ji, Zhiyu Chen, Guibin He, Junceng Guo, Yang Liu, Xinhua Zeng
Abstract: With the rapid development of digital pathology, virtual staining has become a key technology in multimedia medical information systems, offering new possibilities for the analysis and diagnosis of pathological images. However, existing H&E-to-IHC studies often overlook the cross-channel correlations between cell nuclei and cell membranes. To address this issue, we propose a novel Cross-Channel Perception Learning (CCPL) strategy. Specifically, CCPL first decomposes HER2 immunohistochemical staining into Hematoxylin and DAB staining channels, corresponding to cell nuclei and cell membranes, respectively. Using the pathology foundation model Gigapath's Tile Encoder, CCPL extracts dual-channel features from both the generated and real images and measures cross-channel correlations between nuclei and membranes. The features of the generated and real stained images, obtained through the Tile Encoder, are also used to calculate feature distillation loss, enhancing the model's feature extraction capabilities without increasing the inference burden. Additionally, CCPL performs statistical analysis on the focal optical density maps of both single channels to ensure consistency in staining distribution and intensity. Experimental results, based on quantitative metrics such as PSNR, SSIM, PCC, and FID, along with professional evaluations from pathologists, demonstrate that CCPL effectively preserves pathological features, generates high-quality virtual stained images, and provides robust support for automated pathological diagnosis using multimedia medical data.
Authors: Jinlu Zhang, Zixi Kang, Yizhou Wang
Abstract: Music-driven dance generation offers significant creative potential yet faces considerable challenges. The absence of fine-grained multimodal data and the difficulty of flexible multi-conditional generation limit previous works on generation controllability and diversity in practice. In this paper, we build OpenDance5D, an extensive human dance dataset comprising over 101 hours across 14 distinct genres. Each sample has five modalities to facilitate robust cross-modal learning: RGB video, audio, 2D keypoints, 3D motion, and fine-grained textual descriptions from human arts. Furthermore, we propose OpenDanceNet, a unified masked modeling framework for controllable dance generation conditioned on music and arbitrary combinations of text prompts, keypoints, or character positioning. Comprehensive experiments demonstrate that OpenDanceNet achieves high-fidelity and flexible controllability.
Authors: Marco Peer, Robert Sablatnig, Florian Kleber
Abstract: This paper investigates the task of writer retrieval, which identifies documents authored by the same individual within a dataset based on handwriting similarities. While existing datasets and methodologies primarily focus on page level retrieval, we explore the impact of text quantity on writer retrieval performance by evaluating line- and word level retrieval. We examine three state-of-the-art writer retrieval systems, including both handcrafted and deep learning-based approaches, and analyze their performance using varying amounts of text. Our experiments on the CVL and IAM dataset demonstrate that while performance decreases by 20-30% when only one line of text is used as query and gallery, retrieval accuracy remains above 90% of full-page performance when at least four lines are included. We further show that text-dependent retrieval can maintain strong performance in low-text scenarios. Our findings also highlight the limitations of handcrafted features in low-text scenarios, with deep learning-based methods like NetVLAD outperforming traditional VLAD encoding.
Authors: Yixuan Yang, Zhen Luo, Tongsheng Ding, Junru Lu, Mingqi Gao, Jinyu Yang, Victor Sanchez, Feng Zheng
Abstract: Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e.g., GPT APIs) and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a 'GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17,000 scenes, covering four common room types -- bedroom, living room, kitchen, and bathroom -- enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation.
Authors: Yu Li, Feng Xue, Shujie Li, Jinrui Zhang, Shuang Yang, Dan Guo, Richang Hong
Abstract: Lipreading is a challenging cross-modal task that aims to convert visual lip movements into spoken text. Existing lipreading methods often extract visual features that include speaker-specific lip attributes (e.g., shape, color, texture), which introduce spurious correlations between vision and text. These correlations lead to suboptimal lipreading accuracy and restrict model generalization. To address this challenge, we introduce SIFLip, a speaker-invariant visual feature learning framework that disentangles speaker-specific attributes using two complementary disentanglement modules (Implicit Disentanglement and Explicit Disentanglement) to improve generalization. Specifically, since different speakers exhibit semantic consistency between lip movements and phonetic text when pronouncing the same words, our implicit disentanglement module leverages stable text embeddings as supervisory signals to learn common visual representations across speakers, implicitly decoupling speaker-specific features. Additionally, we design a speaker recognition sub-task within the main lipreading pipeline to filter speaker-specific features, then further explicitly disentangle these personalized visual features from the backbone network via gradient reversal. Experimental results demonstrate that SIFLip significantly enhances generalization performance across multiple public datasets. Experimental results demonstrate that SIFLip significantly improves generalization performance across multiple public datasets, outperforming state-of-the-art methods.
Authors: Ruiyang Zhang, Hu Zhang, Hao Fei, Zhedong Zheng
Abstract: Large Multimodal Models (LMMs), harnessing the complementarity among diverse modalities, are often considered more robust than pure Language Large Models (LLMs); yet do LMMs know what they do not know? There are three key open questions remaining: (1) how to evaluate the uncertainty of diverse LMMs in a unified manner, (2) how to prompt LMMs to show its uncertainty, and (3) how to quantify uncertainty for downstream tasks. In an attempt to address these challenges, we introduce Uncertainty-o: (1) a model-agnostic framework designed to reveal uncertainty in LMMs regardless of their modalities, architectures, or capabilities, (2) an empirical exploration of multimodal prompt perturbations to uncover LMM uncertainty, offering insights and findings, and (3) derive the formulation of multimodal semantic uncertainty, which enables quantifying uncertainty from multimodal responses. Experiments across 18 benchmarks spanning various modalities and 10 LMMs (both open- and closed-source) demonstrate the effectiveness of Uncertainty-o in reliably estimating LMM uncertainty, thereby enhancing downstream tasks such as hallucination detection, hallucination mitigation, and uncertainty-aware Chain-of-Thought reasoning.
Authors: Boyu Chen, Siran Chen, Kunchang Li, Qinglin Xu, Yu Qiao, Yali Wang
Abstract: Video understanding has been considered as one critical step towards world modeling, which is an important long-term problem in AI research. Recently, multi-modal foundation models have shown such potential via large-scale pretraining. However, these models simply align encoders of different modalities via contrastive learning, while lacking deeper multi-modal interactions, which is critical for understanding complex target movements with diversified video scenes. To fill this gap, we propose a unified Super Encoding Network (SEN) for video understanding, which builds up such distinct interactions through recursive association of multi-modal encoders in the foundation models. Specifically, we creatively treat those well-trained encoders as "super neurons" in our SEN. Via designing a Recursive Association (RA) block, we progressively fuse multi-modalities with the input video, based on knowledge integrating, distributing, and prompting of super neurons in a recursive manner. In this way, our SEN can effectively encode deeper multi-modal interactions, for prompting various video understanding tasks in downstream. Extensive experiments show that, our SEN can remarkably boost the four most representative video tasks, including tracking, recognition, chatting, and editing, e.g., for pixel-level tracking, the average jaccard index improves 2.7%, temporal coherence(TC) drops 8.8% compared to the popular CaDeX++ approach. For one-shot video editing, textual alignment improves 6.4%, and frame consistency increases 4.1% compared to the popular TuneA-Video approach.
Authors: Jiacheng Shi, Yanfu Zhang, Huajie Shao, Ashley Gao
Abstract: Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive information leakage, and the creation of harmful or offensive content that could be exploited maliciously. In this study, we uncover a novel security threat where an attacker leverages diffusion model APIs to generate synthetic images, which are then used to train a high-performing substitute model. This enables the attacker to execute model extraction and transfer-based adversarial attacks on black-box classification models with minimal queries, without needing access to the original training data. The generated images are sufficiently high-resolution and diverse to train a substitute model whose outputs closely match those of the target model. Across the seven benchmarks, including CIFAR and ImageNet subsets, our method shows an average improvement of 27.37% over state-of-the-art methods while using just 0.01 times of the query budget, achieving a 98.68% success rate in adversarial attacks on the target model.
Authors: Nianbo Zeng, Haowen Hou, Fei Richard Yu, Si Shi, Ying Tiffany He
Abstract: Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches typically segment videos into fixed-length chunks, which often disrupts the continuity of contextual information and fails to capture authentic scene boundaries. Inspired by the human ability to naturally organize continuous experiences into coherent scenes, we present SceneRAG, a unified framework that leverages large language models to segment videos into narrative-consistent scenes by processing ASR transcripts alongside temporal metadata. SceneRAG further sharpens these initial boundaries through lightweight heuristics and iterative correction. For each scene, the framework fuses information from both visual and textual modalities to extract entity relations and dynamically builds a knowledge graph, enabling robust multi-hop retrieval and generation that account for long-range dependencies. Experiments on the LongerVideos benchmark, featuring over 134 hours of diverse content, confirm that SceneRAG substantially outperforms prior baselines, achieving a win rate of up to 72.5 percent on generation tasks.
Authors: Jianhui Wei, Zikai Xiao, Danyu Sun, Luqi Gong, Zongxin Yang, Zuozhu Liu, Jian Wu
Abstract: Surgical video understanding is pivotal for enabling automated intraoperative decision-making, skill assessment, and postoperative quality improvement. However, progress in developing surgical video foundation models (FMs) remains hindered by the scarcity of large-scale, diverse datasets for pretraining and systematic evaluation. In this paper, we introduce \textbf{SurgBench}, a unified surgical video benchmarking framework comprising a pretraining dataset, \textbf{SurgBench-P}, and an evaluation benchmark, \textbf{SurgBench-E}. SurgBench offers extensive coverage of diverse surgical scenarios, with SurgBench-P encompassing 53 million frames across 22 surgical procedures and 11 specialties, and SurgBench-E providing robust evaluation across six categories (phase classification, camera motion, tool recognition, disease diagnosis, action classification, and organ detection) spanning 72 fine-grained tasks. Extensive experiments reveal that existing video FMs struggle to generalize across varied surgical video analysis tasks, whereas pretraining on SurgBench-P yields substantial performance improvements and superior cross-domain generalization to unseen procedures and modalities. Our dataset and code are available upon request.
Authors: Yuan Zhou, Junbao Zhou, Qingshan Xu, Kesen Zhao, Yuxuan Wang, Hao Fei, Richang Hong, Hanwang Zhang
Abstract: Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges: (\emph{\textcolor{magenta}{i}}) point-based drag is often highly ambiguous and difficult to align with users' intentions; (\emph{\textcolor{magenta}{ii}}) current DBIE methods primarily rely on alternating between motion supervision and point tracking, which is not only cumbersome but also fails to produce high-quality results. These limitations motivate us to explore DBIE from a new perspective -- redefining it as deformation, rotation, and translation of user-specified handle regions. Thereby, by requiring users to explicitly specify both drag areas and types, we can effectively address the ambiguity issue. Furthermore, we propose a simple-yet-effective editing framework, dubbed \textcolor{SkyBlue}{\textbf{DragNeXt}}. It unifies DBIE as a Latent Region Optimization (LRO) problem and solves it through Progressive Backward Self-Intervention (PBSI), simplifying the overall procedure of DBIE while further enhancing quality by fully leveraging region-level structure information and progressive guidance from intermediate drag states. We validate \textcolor{SkyBlue}{\textbf{DragNeXt}} on our NextBench, and extensive experiments demonstrate that our proposed method can significantly outperform existing approaches. Code will be released on github.
Authors: Zikang Leng, Archith Iyer, Thomas Pl\"otz
Abstract: Human activity recognition (HAR) is often limited by the scarcity of labeled datasets due to the high cost and complexity of real-world data collection. To mitigate this, recent work has explored generating virtual inertial measurement unit (IMU) data via cross-modality transfer. While video-based and language-based pipelines have each shown promise, they differ in assumptions and computational cost. Moreover, their effectiveness relative to traditional sensor-level data augmentation remains unclear. In this paper, we present a direct comparison between these two virtual IMU generation approaches against classical data augmentation techniques. We construct a large-scale virtual IMU dataset spanning 100 diverse activities from Kinetics-400 and simulate sensor signals at 22 body locations. The three data generation strategies are evaluated on benchmark HAR datasets (UTD-MHAD, PAMAP2, HAD-AW) using four popular models. Results show that virtual IMU data significantly improves performance over real or augmented data alone, particularly under limited-data conditions. We offer practical guidance on choosing data generation strategies and highlight the distinct advantages and disadvantages of each approach.
Authors: Haotong Qin, Cheng Hu, Michele Magno
Abstract: Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge devices. A key source of inefficiency stems from the VLM's need to process dense and redundant visual information. Visual inputs contain significant regions irrelevant to text semantics, rendering the associated computations ineffective for inference. This paper introduces a novel Event-Priori-Based Vision-Language Model, termed EP-VLM. Its core contribution is a novel mechanism leveraging motion priors derived from dynamic event vision to enhance VLM efficiency. Inspired by human visual cognition, EP-VLM first employs event data to guide the patch-wise sparsification of RGB visual inputs, progressively concentrating VLM computation on salient regions of the visual input. Subsequently, we construct a position-preserving tokenization strategy for the visual encoder within the VLM architecture. This strategy processes the event-guided, unstructured, sparse visual input while accurately preserving positional understanding within the visual input. Experimental results demonstrate that EP-VLM achieves significant efficiency improvements while maintaining nearly lossless accuracy compared to baseline models from the Qwen2-VL series. For instance, against the original Qwen2-VL-2B, EP-VLM achieves 50% FLOPs savings while retaining 98% of the original accuracy on the RealWorldQA dataset. This work demonstrates the potential of event-based vision priors for improving VLM inference efficiency, paving the way for creating more efficient and deployable VLMs for sustainable visual understanding at the edge.
Authors: Weronika Smolak-Dy\.zewska, Dawid Malarz, Grzegorz Wilczy\'nski, Rafa{\l} Tobiasz, Joanna Waczy\'nska, Piotr Borycki, Przemys{\l}aw Spurek
Abstract: 3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic or meticulously captured realistic data. Such benchmarks fail to convey the inherent complexities encountered in newly acquired real-world scenes. In such scenes especially those acquired outside, the background is often dynamic, and by popular usage of cell phone cameras, there might be discrepancies in, e.g., white balance. To address this gap, we present HuSc3D, a novel dataset specifically designed for rigorous benchmarking of 3D reconstruction models under realistic acquisition challenges. Our dataset uniquely features six highly detailed, fully white sculptures characterized by intricate perforations and minimal textural and color variation. Furthermore, the number of images per scene varies significantly, introducing the additional challenge of limited training data for some instances alongside scenes with a standard number of views. By evaluating popular 3D reconstruction methods on this diverse dataset, we demonstrate the distinctiveness of HuSc3D in effectively differentiating model performance, particularly highlighting the sensitivity of methods to fine geometric details, color ambiguity, and varying data availability--limitations often masked by more conventional datasets.
Authors: Yuchong Long, Wen Sun, Ningxiao Sun, Wenxiao Wang, Chao Li, Shan Yin
Abstract: Automated pollen recognition is vital to paleoclimatology, biodiversity monitoring, and public health, yet conventional methods are hampered by inefficiency and subjectivity. Existing deep learning models often struggle to achieve the requisite localization accuracy for microscopic targets like pollen, which are characterized by their minute size, indistinct edges, and complex backgrounds. To overcome this limitation, we introduce HieraEdgeNet, a multi-scale edge-enhancement framework. The framework's core innovation is the introduction of three synergistic modules: the Hierarchical Edge Module (HEM), which explicitly extracts a multi-scale pyramid of edge features that corresponds to the semantic hierarchy at early network stages; the Synergistic Edge Fusion (SEF) module, for deeply fusing these edge priors with semantic information at each respective scale; and the Cross Stage Partial Omni-Kernel Module (CSPOKM), which maximally refines the most detail-rich feature layers using an Omni-Kernel operator - comprising anisotropic large-kernel convolutions and mixed-domain attention - all within a computationally efficient Cross-Stage Partial (CSP) framework. On a large-scale dataset comprising 120 pollen classes, HieraEdgeNet achieves a mean Average Precision (mAP@.5) of 0.9501, significantly outperforming state-of-the-art baseline models such as YOLOv12n and RT-DETR. Furthermore, qualitative analysis confirms that our approach generates feature representations that are more precisely focused on object boundaries. By systematically integrating edge information, HieraEdgeNet provides a robust and powerful solution for high-precision, high-efficiency automated detection of microscopic objects.
Authors: Jae Sung Park, Zixian Ma, Linjie Li, Chenhao Zheng, Cheng-Yu Hsieh, Ximing Lu, Khyathi Chandu, Quan Kong, Norimasa Kobori, Ali Farhadi, Yejin Choi, Ranjay Krishna
Abstract: Reasoning over visual relationships-spatial, functional, interactional, social, etc.-is considered to be a fundamental component of human cognition. Yet, despite the major advances in visual comprehension in multimodal language models (MLMs), precise reasoning over relationships and their generations remains a challenge. We introduce ROBIN: an MLM instruction-tuned with densely annotated relationships capable of constructing high-quality dense scene graphs at scale. To train ROBIN, we curate SVG, a synthetic scene graph dataset by completing the missing relations of selected objects in existing scene graphs using a teacher MLM and a carefully designed filtering process to ensure high-quality. To generate more accurate and rich scene graphs at scale for any image, we introduce SG-EDIT: a self-distillation framework where GPT-4o further refines ROBIN's predicted scene graphs by removing unlikely relations and/or suggesting relevant ones. In total, our dataset contains 146K images and 5.6M relationships for 2.6M objects. Results show that our ROBIN-3B model, despite being trained on less than 3 million instances, outperforms similar-size models trained on over 300 million instances on relationship understanding benchmarks, and even surpasses larger models up to 13B parameters. Notably, it achieves state-of-the-art performance in referring expression comprehension with a score of 88.9, surpassing the previous best of 87.4. Our results suggest that training on the refined scene graph data is crucial to maintaining high performance across diverse visual reasoning task.
Authors: Hangbei Cheng, Xiaorong Dong, Xueyu Liu, Jianan Zhang, Xuetao Ma, Mingqiang Wei, Liansheng Wang, Junxin Chen, Yongfei Wu
Abstract: Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availability of costly pixel-level annotations. To address this, we propose FMaMIL, a novel two-stage framework for weakly supervised lesion segmentation based solely on image-level labels. In the first stage, a lightweight Mamba-based encoder is introduced to capture long-range dependencies across image patches under the MIL paradigm. To enhance spatial sensitivity and structural awareness, we design a learnable frequency-domain encoding module that supplements spatial-domain features with spectrum-based information. CAMs generated in this stage are used to guide segmentation training. In the second stage, we refine the initial pseudo labels via a CAM-guided soft-label supervision and a self-correction mechanism, enabling robust training even under label noise. Extensive experiments on both public and private histopathology datasets demonstrate that FMaMIL outperforms state-of-the-art weakly supervised methods without relying on pixel-level annotations, validating its effectiveness and potential for digital pathology applications.
Authors: Xiaohan Lu, Jiaye Fu, Jiaqi Zhang, Zetian Song, Chuanmin Jia, Siwei Ma
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) has recently demonstrated promising results for novel view synthesis (NVS) from sparse input views, particularly under narrow-baseline conditions. However, its performance significantly degrades in wide-baseline scenarios due to limited texture details and geometric inconsistencies across views. To address these challenges, in this paper, we propose ProSplat, a two-stage feed-forward framework designed for high-fidelity rendering under wide-baseline conditions. The first stage involves generating 3D Gaussian primitives via a 3DGS generator. In the second stage, rendered views from these primitives are enhanced through an improvement model. Specifically, this improvement model is based on a one-step diffusion model, further optimized by our proposed Maximum Overlap Reference view Injection (MORI) and Distance-Weighted Epipolar Attention (DWEA). MORI supplements missing texture and color by strategically selecting a reference view with maximum viewpoint overlap, while DWEA enforces geometric consistency using epipolar constraints. Additionally, we introduce a divide-and-conquer training strategy that aligns data distributions between the two stages through joint optimization. We evaluate ProSplat on the RealEstate10K and DL3DV-10K datasets under wide-baseline settings. Experimental results demonstrate that ProSplat achieves an average improvement of 1 dB in PSNR compared to recent SOTA methods.
Authors: Jens Piekenbrinck, Christian Schmidt, Alexander Hermans, Narunas Vaskevicius, Timm Linder, Bastian Leibe
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational efficiency. In this paper, we extend the capabilities of 3DGS beyond pure scene representation by introducing an approach for open-vocabulary 3D instance segmentation without requiring manual labeling, termed OpenSplat3D. Our method leverages feature-splatting techniques to associate semantic information with individual Gaussians, enabling fine-grained scene understanding. We incorporate Segment Anything Model instance masks with a contrastive loss formulation as guidance for the instance features to achieve accurate instance-level segmentation. Furthermore, we utilize language embeddings of a vision-language model, allowing for flexible, text-driven instance identification. This combination enables our system to identify and segment arbitrary objects in 3D scenes based on natural language descriptions. We show results on LERF-mask and LERF-OVS as well as the full ScanNet++ validation set, demonstrating the effectiveness of our approach.
Authors: Yuxiao Yang, Peihao Li, Yuhong Zhang, Junzhe Lu, Xianglong He, Minghan Qin, Weitao Wang, Haoqian Wang
Abstract: 3D AI-generated content (AIGC) has made it increasingly accessible for anyone to become a 3D content creator. While recent methods leverage Score Distillation Sampling to distill 3D objects from pretrained image diffusion models, they often suffer from inadequate 3D priors, leading to insufficient multi-view consistency. In this work, we introduce NOVA3D, an innovative single-image-to-3D generation framework. Our key insight lies in leveraging strong 3D priors from a pretrained video diffusion model and integrating geometric information during multi-view video fine-tuning. To facilitate information exchange between color and geometric domains, we propose the Geometry-Temporal Alignment (GTA) attention mechanism, thereby improving generalization and multi-view consistency. Moreover, we introduce the de-conflict geometry fusion algorithm, which improves texture fidelity by addressing multi-view inaccuracies and resolving discrepancies in pose alignment. Extensive experiments validate the superiority of NOVA3D over existing baselines.
Authors: Weilei Wen, Chunle Guo, Wenqi Ren, Hongpeng Wang, Xiuli Shao
Abstract: Prior methodologies have disregarded the diversities among distinct degradation types during image reconstruction, employing a uniform network model to handle multiple deteriorations. Nevertheless, we discover that prevalent degradation modalities, including sampling, blurring, and noise, can be roughly categorized into two classes. We classify the first class as spatial-agnostic dominant degradations, less affected by regional changes in image space, such as downsampling and noise degradation. The second class degradation type is intimately associated with the spatial position of the image, such as blurring, and we identify them as spatial-specific dominant degradations. We introduce a dynamic filter network integrating global and local branches to address these two degradation types. This network can greatly alleviate the practical degradation problem. Specifically, the global dynamic filtering layer can perceive the spatial-agnostic dominant degradation in different images by applying weights generated by the attention mechanism to multiple parallel standard convolution kernels, enhancing the network's representation ability. Meanwhile, the local dynamic filtering layer converts feature maps of the image into a spatially specific dynamic filtering operator, which performs spatially specific convolution operations on the image features to handle spatial-specific dominant degradations. By effectively integrating both global and local dynamic filtering operators, our proposed method outperforms state-of-the-art blind super-resolution algorithms in both synthetic and real image datasets.
Authors: Ge Wang, Songlin Fan, Hangxu Liu, Quanjian Song, Hewei Wang, Jinfeng Xu
Abstract: With the prosper of video diffusion models, down-stream applications like video editing have been significantly promoted without consuming much computational cost. One particular challenge in this task lies at the motion transfer process from the source video to the edited one, where it requires the consideration of the shape deformation in between, meanwhile maintaining the temporal consistency in the generated video sequence. However, existing methods fail to model complicated motion patterns for video editing, and are fundamentally limited to object replacement, where tasks with non-rigid object motions like multi-object and portrait editing are largely neglected. In this paper, we observe that optical flows offer a promising alternative in complex motion modeling, and present FlowV2V to re-investigate video editing as a task of flow-driven Image-to-Video (I2V) generation. Specifically, FlowV2V decomposes the entire pipeline into first-frame editing and conditional I2V generation, and simulates pseudo flow sequence that aligns with the deformed shape, thus ensuring the consistency during editing. Experimental results on DAVIS-EDIT with improvements of 13.67% and 50.66% on DOVER and warping error illustrate the superior temporal consistency and sample quality of FlowV2V compared to existing state-of-the-art ones. Furthermore, we conduct comprehensive ablation studies to analyze the internal functionalities of the first-frame paradigm and flow alignment in the proposed method.
Authors: Yufei Guo, Yuhan Zhang, Zhou Jie, Xiaode Liu, Xin Tong, Yuanpei Chen, Weihang Peng, Zhe Ma
Abstract: The Spiking Neural Network (SNN), a biologically inspired neural network infrastructure, has garnered significant attention recently. SNNs utilize binary spike activations for efficient information transmission, replacing multiplications with additions, thereby enhancing energy efficiency. However, binary spike activation maps often fail to capture sufficient data information, resulting in reduced accuracy. To address this challenge, we advocate reversing the bit of the weight and activation for SNNs, called \textbf{ReverB-SNN}, inspired by recent findings that highlight greater accuracy degradation from quantizing activations compared to weights. Specifically, our method employs real-valued spike activations alongside binary weights in SNNs. This preserves the event-driven and multiplication-free advantages of standard SNNs while enhancing the information capacity of activations. Additionally, we introduce a trainable factor within binary weights to adaptively learn suitable weight amplitudes during training, thereby increasing network capacity. To maintain efficiency akin to vanilla \textbf{ReverB-SNN}, our trainable binary weight SNNs are converted back to standard form using a re-parameterization technique during inference. Extensive experiments across various network architectures and datasets, both static and dynamic, demonstrate that our approach consistently outperforms state-of-the-art methods.
Authors: Shadi Hamdan, Chonghao Sima, Zetong Yang, Hongyang Li, Fatma G\"uney
Abstract: How can we benefit from large models without sacrificing inference speed, a common dilemma in self-driving systems? A prevalent solution is a dual-system architecture, employing a small model for rapid, reactive decisions and a larger model for slower but more informative analyses. Existing dual-system designs often implement parallel architectures where inference is either directly conducted using the large model at each current frame or retrieved from previously stored inference results. However, these works still struggle to enable large models for a timely response to every online frame. Our key insight is to shift intensive computations of the current frame to previous time steps and perform a batch inference of multiple time steps to make large models respond promptly to each time step. To achieve the shifting, we introduce Efficiency through Thinking Ahead (ETA), an asynchronous system designed to: (1) propagate informative features from the past to the current frame using future predictions from the large model, (2) extract current frame features using a small model for real-time responsiveness, and (3) integrate these dual features via an action mask mechanism that emphasizes action-critical image regions. Evaluated on the Bench2Drive CARLA Leaderboard-v2 benchmark, ETA advances state-of-the-art performance by 8% with a driving score of 69.53 while maintaining a near-real-time inference speed at 50 ms.
Authors: Xuemei Chen, Huamin Wang, Hangchi Shen, Shukai Duan, Shiping Wen, Tingwen Huang
Abstract: Low energy consumption for 3D object detection is an important research area because of the increasing energy consumption with their wide application in fields such as autonomous driving. The spiking neural networks (SNNs) with low-power consumption characteristics can provide a novel solution for this research. Therefore, we apply SNNs to monocular 3D object detection and propose the SpikeSMOKE architecture in this paper, which is a new attempt for low-power monocular 3D object detection. As we all know, discrete signals of SNNs will generate information loss and limit their feature expression ability compared with the artificial neural networks (ANNs).In order to address this issue, inspired by the filtering mechanism of biological neuronal synapses, we propose a cross-scale gated coding mechanism(CSGC), which can enhance feature representation by combining cross-scale fusion of attentional methods and gated filtering mechanisms.In addition, to reduce the computation and increase the speed of training, we present a novel light-weight residual block that can maintain spiking computing paradigm and the highest possible detection performance. Compared to the baseline SpikeSMOKE under the 3D Object Detection, the proposed SpikeSMOKE with CSGC can achieve 11.78 (+2.82, Easy), 10.69 (+3.2, Moderate), and 10.48 (+3.17, Hard) on the KITTI autonomous driving dataset by AP|R11 at 0.7 IoU threshold, respectively. It is important to note that the results of SpikeSMOKE can significantly reduce energy consumption compared to the results on SMOKE. For example,the energy consumption can be reduced by 72.2% on the hard category, while the detection performance is reduced by only 4%. SpikeSMOKE-L (lightweight) can further reduce the amount of parameters by 3 times and computation by 10 times compared to SMOKE.
Authors: Lanjiong Li, Guanhua Zhao, Lingting Zhu, Zeyu Cai, Lequan Yu, Jian Zhang, Zeyu Wang
Abstract: Recent research on generative models has primarily focused on creating product-ready visual outputs; however, designers often favor access to standardized asset libraries, a domain that has yet to be significantly enhanced by generative capabilities. Although open-world scenes provide ample raw materials for designers, efficiently extracting high-quality, standardized assets remains a challenge. To address this, we introduce AssetDropper, the first framework designed to extract assets from reference images, providing artists with an open-world asset palette. Our model adeptly extracts a front view of selected subjects from input images, effectively handling complex scenarios such as perspective distortion and subject occlusion. We establish a synthetic dataset of more than 200,000 image-subject pairs and a real-world benchmark with thousands more for evaluation, facilitating the exploration of future research in downstream tasks. Furthermore, to ensure precise asset extraction that aligns well with the image prompts, we employ a pre-trained reward model to fulfill a closed-loop with feedback. We design the reward model to perform an inverse task that pastes the extracted assets back into the reference sources, which assists training with additional consistency and mitigates hallucination. Extensive experiments show that, with the aid of reward-driven optimization, AssetDropper achieves the state-of-the-art results in asset extraction. Project page: AssetDropper.github.io.
Authors: Jing Zhong, Jun Yin, Peilin Li, Pengyu Zeng, Miao Zang, Ran Luo, Shuai Lu
Abstract: Architectural cultures across regions are characterized by stylistic diversity, shaped by historical, social, and technological contexts in addition to geograph-ical conditions. Understanding architectural styles requires the ability to describe and analyze the stylistic features of different architects from various regions through visual observations of architectural imagery. However, traditional studies of architectural culture have largely relied on subjective expert interpretations and historical literature reviews, often suffering from regional biases and limited ex-planatory scope. To address these challenges, this study proposes three core contributions: (1) We construct a professional architectural style dataset named ArchDiffBench, which comprises 1,765 high-quality architectural images and their corresponding style annotations, collected from different regions and historical periods. (2) We propose ArchiLense, an analytical framework grounded in Vision-Language Models and constructed using the ArchDiffBench dataset. By integrating ad-vanced computer vision techniques, deep learning, and machine learning algo-rithms, ArchiLense enables automatic recognition, comparison, and precise classi-fication of architectural imagery, producing descriptive language outputs that ar-ticulate stylistic differences. (3) Extensive evaluations show that ArchiLense achieves strong performance in architectural style recognition, with a 92.4% con-sistency rate with expert annotations and 84.5% classification accuracy, effec-tively capturing stylistic distinctions across images. The proposed approach transcends the subjectivity inherent in traditional analyses and offers a more objective and accurate perspective for comparative studies of architectural culture.
Authors: Yingping Liang, Ying Fu, Yutao Hu, Wenqi Shao, Jiaming Liu, Debing Zhang
Abstract: Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose \textbf{Flow-Anything}, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely \textbf{FA-Flow Dataset}. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.
Authors: Hyunsoo Kim, Donghyun Kim, Suhyun Kim
Abstract: How can we generate an image B' that satisfies A:A'::B:B', given the input images A,A' and B? Recent works have tackled this challenge through approaches like visual in-context learning or visual instruction. However, these methods are typically limited to specific models (e.g. InstructPix2Pix. Inpainting models) rather than general diffusion models (e.g. Stable Diffusion, SDXL). This dependency may lead to inherited biases or lower editing capabilities. In this paper, we propose Difference Inversion, a method that isolates only the difference from A and A' and applies it to B to generate a plausible B'. To address model dependency, it is crucial to structure prompts in the form of a "Full Prompt" suitable for input to stable diffusion models, rather than using an "Instruction Prompt". To this end, we accurately extract the Difference between A and A' and combine it with the prompt of B, enabling a plug-and-play application of the difference. To extract a precise difference, we first identify it through 1) Delta Interpolation. Additionally, to ensure accurate training, we propose the 2) Token Consistency Loss and 3) Zero Initialization of Token Embeddings. Our extensive experiments demonstrate that Difference Inversion outperforms existing baselines both quantitatively and qualitatively, indicating its ability to generate more feasible B' in a model-agnostic manner.
Authors: Mohamed Djilani, Nassim Ali Ousalah, Nidhal Eddine Chenni
Abstract: We introduce a trend-aware and visually-grounded fashion recommendation system that integrates deep visual representations, garment-aware segmentation, semantic category similarity and user behavior simulation. Our pipeline extracts focused visual embeddings by masking non-garment regions via semantic segmentation followed by feature extraction using pretrained CNN backbones (ResNet-50, DenseNet-121, VGG16). To simulate realistic shopping behavior, we generate synthetic purchase histories influenced by user-specific trendiness and item popularity. Recommendations are computed using a weighted scoring function that fuses visual similarity, semantic coherence and popularity alignment. Experiments on the DeepFashion dataset demonstrate consistent gender alignment and improved category relevance, with ResNet-50 achieving 64.95% category similarity and lowest popularity MAE. An ablation study confirms the complementary roles of visual and popularity cues. Our method provides a scalable framework for personalized fashion recommendations that balances individual style with emerging trends. Our implementation is available at https://github.com/meddjilani/FashionRecommender
Authors: Yichang Xu, Gaowen Liu, Ramana Rao Kompella, Sihao Hu, Tiansheng Huang, Fatih Ilhan, Selim Furkan Tekin, Zachary Yahn, Ling Liu
Abstract: The advancement in large language models (LLMs) and large vision models has fueled the rapid progress in multi-modal visual-text reasoning capabilities. However, existing vision-language models (VLMs) to date suffer from generalization performance. Inspired by recent development in LLMs for visual reasoning, this paper presents VLAgent, an AI system that can create a step-by-step visual reasoning plan with an easy-to-understand script and execute each step of the plan in real time by integrating planning script with execution verifications via an automated process supported by VLAgent. In the task planning phase, VLAgent fine-tunes an LLM through in-context learning to generate a step-by-step planner for each user-submitted text-visual reasoning task. During the plan execution phase, VLAgent progressively refines the composition of neuro-symbolic executable modules to generate high-confidence reasoning results. VLAgent has three unique design characteristics: First, we improve the quality of plan generation through in-context learning, improving logic reasoning by reducing erroneous logic steps, incorrect programs, and LLM hallucinations. Second, we design a syntax-semantics parser to identify and correct additional logic errors of the LLM-generated planning script prior to launching the plan executor. Finally, we employ the ensemble method to improve the generalization performance of our step-executor. Extensive experiments with four visual reasoning benchmarks (GQA, MME, NLVR2, VQAv2) show that VLAgent achieves significant performance enhancement for multimodal text-visual reasoning applications, compared to the exiting representative VLMs and LLM based visual composition approaches like ViperGPT and VisProg, thanks to the novel optimization modules of VLAgent back-engine (SS-Parser, Plan Repairer, Output Verifiers). Code and data will be made available upon paper acceptance.
Authors: Beining Xu, Junxian Li
Abstract: Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently, deep learning-based fusion methods have gained attention, but current evaluations primarily rely on general-purpose metrics without standardized benchmarks or downstream task performance. Additionally, the lack of well-developed dual-spectrum datasets and fair algorithm comparisons hinders progress. To address these gaps, we construct a high-quality dual-spectrum dataset captured in campus environments, comprising 1,369 well-aligned visible-infrared image pairs across four representative scenarios: daytime, nighttime, smoke occlusion, and underpasses. We also propose a comprehensive and fair evaluation framework that integrates fusion speed, general metrics, and object detection performance using the lang-segment-anything model to ensure fairness in downstream evaluation. Extensive experiments benchmark several state-of-the-art fusion algorithms under this framework. Results demonstrate that fusion models optimized for downstream tasks achieve superior performance in target detection, especially in low-light and occluded scenes. Notably, some algorithms that perform well on general metrics do not translate to strong downstream performance, highlighting limitations of current evaluation practices and validating the necessity of our proposed framework. The main contributions of this work are: (1)a campus-oriented dual-spectrum dataset with diverse and challenging scenes; (2) a task-aware, comprehensive evaluation framework; and (3) thorough comparative analysis of leading fusion methods across multiple datasets, offering insights for future development.
Authors: Qi Yang, Chenghao Zhang, Lubin Fan, Kun Ding, Jieping Ye, Shiming Xiang
Abstract: Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks through multimodal Retrieval-Augmented Generation (RAG). However, existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge. To address these issues, in this study, we propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method. Specifically, we introduce a self-consistent evaluation mechanism to enrich the knowledge base with intrinsic reasoning patterns. We further propose a Monte Carlo Tree Search with Heuristic Rewards (MCTS-HR) to prioritize the most relevant examples. This ensures that LVLMs can leverage high-quality contextual reasoning for better and more consistent responses. Extensive experiments demonstrate that our framework achieves state-of-the-art performance on multiple VQA datasets, significantly outperforming In-Context Learning (ICL) and Vanilla-RAG methods. It highlights the effectiveness of our knowledge base and re-ranking method in improving LVLMs. Our code is available at https://github.com/yannqi/RCTS-RAG.
Authors: Eduard Allakhverdov, Dmitrii Tarasov, Elizaveta Goncharova, Andrey Kuznetsov
Abstract: Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures represent features internally. Here, we propose a novel approach for interpreting vision features via image reconstruction. We compare two related model families, SigLIP and SigLIP2, which differ only in their training objective, and show that encoders pre-trained on image-based tasks retain significantly more image information than those trained on non-image tasks such as contrastive learning. We further apply our method to a range of vision encoders, ranking them by the informativeness of their feature representations. Finally, we demonstrate that manipulating the feature space yields predictable changes in reconstructed images, revealing that orthogonal rotations (rather than spatial transformations) control color encoding. Our approach can be applied to any vision encoder, shedding light on the inner structure of its feature space. The code and model weights to reproduce the experiments are available in GitHub.
Authors: Weilei Wen, Tianyi Zhang, Qianqian Zhao, Zhaohui Zheng, Chunle Guo, Xiuli Shao, Chongyi Li
Abstract: Recent advancements in codebook-based real image super-resolution (SR) have shown promising results in real-world applications. The core idea involves matching high-quality image features from a codebook based on low-resolution (LR) image features. However, existing methods face two major challenges: inaccurate feature matching with the codebook and poor texture detail reconstruction. To address these issues, we propose a novel Uncertainty-Guided and Top-k Codebook Matching SR (UGTSR) framework, which incorporates three key components: (1) an uncertainty learning mechanism that guides the model to focus on texture-rich regions, (2) a Top-k feature matching strategy that enhances feature matching accuracy by fusing multiple candidate features, and (3) an Align-Attention module that enhances the alignment of information between LR and HR features. Experimental results demonstrate significant improvements in texture realism and reconstruction fidelity compared to existing methods. We will release the code upon formal publication.
Authors: Tieyuan Chen, Huabin Liu, Yi Wang, Chaofan Gan, Mingxi Lyu, Gui Zou, Weiyao Lin
Abstract: Video Question Answering (VideoQA) aims to answer natural language questions based on the given video, with prior work primarily focusing on identifying the duration of relevant segments, referred to as explicit visual evidence. However, explicit visual evidence is not always directly available, particularly when questions target symbolic meanings or deeper intentions, leading to significant performance degradation. To fill this gap, we introduce a novel task and dataset, $\textbf{I}$mplicit $\textbf{V}$ideo $\textbf{Q}$uestion $\textbf{A}$nswering (I-VQA), which focuses on answering questions in scenarios where explicit visual evidence is inaccessible. Given an implicit question and its corresponding video, I-VQA requires answering based on the contextual visual cues present within the video. To tackle I-VQA, we propose a novel reasoning framework, IRM (Implicit Reasoning Model), incorporating dual-stream modeling of contextual actions and intent clues as implicit reasoning chains. IRM comprises the Action-Intent Module (AIM) and the Visual Enhancement Module (VEM). AIM deduces and preserves question-related dual clues by generating clue candidates and performing relation deduction. VEM enhances contextual visual representation by leveraging key contextual clues. Extensive experiments validate the effectiveness of our IRM in I-VQA tasks, outperforming GPT-4o, OpenAI-o3, and fine-tuned VideoChat2 by $0.76\%$, $1.37\%$, and $4.87\%$, respectively. Additionally, IRM performs SOTA on similar implicit advertisement understanding and future prediction in traffic-VQA. Datasets and codes are available for double-blind review in anonymous repo: https://github.com/tychen-SJTU/Implicit-VideoQA.
Authors: Junseo Bang, Joonhee Lee, Kyeonghyun Lee, Haechang Lee, Dong Un Kang, Se Young Chun
Abstract: Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches in this domain utilize regression-based or generative models, but many of them are a single-stage upsampling process, which may be challenging to learn across a wide, continuous distribution of scaling factors. Progressive upsampling strategies have shown promise in mitigating this issue, yet their integration with diffusion models for flexible upscaling remains underexplored. Here, we present CasArbi, a novel self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi meets the varying scaling demands by breaking them down into smaller sequential factors and progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. Our novel coordinate-guided residual diffusion model allows for the learning of continuous image representations while enabling efficient diffusion sampling. Extensive experiments demonstrate that our CasArbi outperforms prior arts in both perceptual and distortion performance metrics across diverse arbitrary-scale super-resolution benchmarks.
Authors: Yongzhen Wang, Yongjun Li, Zhuoran Zheng, Xiao-Ping Zhang, Mingqiang Wei
Abstract: Natural images are often degraded by complex, composite degradations such as rain, snow, and haze, which adversely impact downstream vision applications. While existing image restoration efforts have achieved notable success, they are still hindered by two critical challenges: limited generalization across dynamically varying degradation scenarios and a suboptimal balance between preserving local details and modeling global dependencies. To overcome these challenges, we propose M2Restore, a novel Mixture-of-Experts (MoE)-based Mamba-CNN fusion framework for efficient and robust all-in-one image restoration. M2Restore introduces three key contributions: First, to boost the model's generalization across diverse degradation conditions, we exploit a CLIP-guided MoE gating mechanism that fuses task-conditioned prompts with CLIP-derived semantic priors. This mechanism is further refined via cross-modal feature calibration, which enables precise expert selection for various degradation types. Second, to jointly capture global contextual dependencies and fine-grained local details, we design a dual-stream architecture that integrates the localized representational strength of CNNs with the long-range modeling efficiency of Mamba. This integration enables collaborative optimization of global semantic relationships and local structural fidelity, preserving global coherence while enhancing detail restoration. Third, we introduce an edge-aware dynamic gating mechanism that adaptively balances global modeling and local enhancement by reallocating computational attention to degradation-sensitive regions. This targeted focus leads to more efficient and precise restoration. Extensive experiments across multiple image restoration benchmarks validate the superiority of M2Restore in both visual quality and quantitative performance.
Authors: William Ljungbergh, Bernardo Taveira, Wenzhao Zheng, Adam Tonderski, Chensheng Peng, Fredrik Kahl, Christoffer Petersson, Michael Felsberg, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
Abstract: Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, while controllable, are resource-intensive to scale and often suffer from a domain gap with real-world data. In contrast, neural reconstruction methods like 3D Gaussian Splatting (3DGS) offer a scalable solution for creating photorealistic digital twins of real-world driving scenes. However, they struggle with dynamic object manipulation and reusability as their per-scene optimization-based methodology tends to result in incomplete object models with integrated illumination effects. This paper introduces R3D2, a lightweight, one-step diffusion model designed to overcome these limitations and enable realistic insertion of complete 3D assets into existing scenes by generating plausible rendering effects-such as shadows and consistent lighting-in real time. This is achieved by training R3D2 on a novel dataset: 3DGS object assets are generated from in-the-wild AD data using an image-conditioned 3D generative model, and then synthetically placed into neural rendering-based virtual environments, allowing R3D2 to learn realistic integration. Quantitative and qualitative evaluations demonstrate that R3D2 significantly enhances the realism of inserted assets, enabling use-cases like text-to-3D asset insertion and cross-scene/dataset object transfer, allowing for true scalability in AD validation. To promote further research in scalable and realistic AD simulation, we will release our dataset and code, see https://research.zenseact.com/publications/R3D2/.
Authors: Elizabeth Pavlova, Xue-Xin Wei
Abstract: Recent work on diffusion models proposed that they operate in two regimes: memorization, in which models reproduce their training data, and generalization, in which they generate novel samples. While this has been tested in high-noise settings, the behavior of diffusion models as effective denoisers when the corruption level is small remains unclear. To address this gap, we systematically investigated the behavior of diffusion models under low-noise diffusion dynamics, with implications for model robustness and interpretability. Using (i) CelebA subsets of varying sample sizes and (ii) analytic Gaussian mixture benchmarks, we reveal that models trained on disjoint data diverge near the data manifold even when their high-noise outputs converge. We quantify how training set size, data geometry, and model objective choice shape denoising trajectories and affect score accuracy, providing insights into how these models actually learn representations of data distributions. This work starts to address gaps in our understanding of generative model reliability in practical applications where small perturbations are common.
Authors: Hengzhi Chen, Liqian Feng, Wenhua Wu, Xiaogang Zhu, Shawn Leo, Kun Hu
Abstract: Semantic segmentation of ultra-high-resolution (UHR) remote sensing imagery is critical for applications like environmental monitoring and urban planning but faces computational and optimization challenges. Conventional methods either lose fine details through downsampling or fragment global context via patch processing. While multi-branch networks address this trade-off, they suffer from computational inefficiency and conflicting gradient dynamics during training. We propose F2Net, a frequency-aware framework that decomposes UHR images into high- and low-frequency components for specialized processing. The high-frequency branch preserves full-resolution structural details, while the low-frequency branch processes downsampled inputs through dual sub-branches capturing short- and long-range dependencies. A Hybrid-Frequency Fusion module integrates these observations, guided by two novel objectives: Cross-Frequency Alignment Loss ensures semantic consistency between frequency components, and Cross-Frequency Balance Loss regulates gradient magnitudes across branches to stabilize training. Evaluated on DeepGlobe and Inria Aerial benchmarks, F2Net achieves state-of-the-art performance with mIoU of 80.22 and 83.39, respectively. Our code will be publicly available.
Authors: Teng Hu, Zhentao Yu, Zhengguang Zhou, Jiangning Zhang, Yuan Zhou, Qinglin Lu, Ran Yi
Abstract: Despite recent advances in video generation, existing models still lack fine-grained controllability, especially for multi-subject customization with consistent identity and interaction. In this paper, we propose PolyVivid, a multi-subject video customization framework that enables flexible and identity-consistent generation. To establish accurate correspondences between subject images and textual entities, we design a VLLM-based text-image fusion module that embeds visual identities into the textual space for precise grounding. To further enhance identity preservation and subject interaction, we propose a 3D-RoPE-based enhancement module that enables structured bidirectional fusion between text and image embeddings. Moreover, we develop an attention-inherited identity injection module to effectively inject fused identity features into the video generation process, mitigating identity drift. Finally, we construct an MLLM-based data pipeline that combines MLLM-based grounding, segmentation, and a clique-based subject consolidation strategy to produce high-quality multi-subject data, effectively enhancing subject distinction and reducing ambiguity in downstream video generation. Extensive experiments demonstrate that PolyVivid achieves superior performance in identity fidelity, video realism, and subject alignment, outperforming existing open-source and commercial baselines.
Authors: Arash Rocky, Q. M. Jonathan Wu
Abstract: Vision-Language Models (VLMs) lag behind Large Language Models due to the scarcity of annotated datasets, as creating paired visual-textual annotations is labor-intensive and expensive. To address this bottleneck, we introduce SAM2Auto, the first fully automated annotation pipeline for video datasets requiring no human intervention or dataset-specific training. Our approach consists of two key components: SMART-OD, a robust object detection system that combines automatic mask generation with open-world object detection capabilities, and FLASH (Frame-Level Annotation and Segmentation Handler), a multi-object real-time video instance segmentation (VIS) that maintains consistent object identification across video frames even with intermittent detection gaps. Unlike existing open-world detection methods that require frame-specific hyperparameter tuning and suffer from numerous false positives, our system employs statistical approaches to minimize detection errors while ensuring consistent object tracking throughout entire video sequences. Extensive experimental validation demonstrates that SAM2Auto achieves comparable accuracy to manual annotation while dramatically reducing annotation time and eliminating labor costs. The system successfully handles diverse datasets without requiring retraining or extensive parameter adjustments, making it a practical solution for large-scale dataset creation. Our work establishes a new baseline for automated video annotation and provides a pathway for accelerating VLM development by addressing the fundamental dataset bottleneck that has constrained progress in vision-language understanding.
Authors: Zihui Zhang, Weisheng Dai, Hongtao Wen, Bo Yang
Abstract: We study the problem of unsupervised 3D semantic segmentation on raw point clouds without needing human labels in training. Existing methods usually formulate this problem into learning per-point local features followed by a simple grouping strategy, lacking the ability to discover additional and possibly richer semantic priors beyond local features. In this paper, we introduce LogoSP to learn 3D semantics from both local and global point features. The key to our approach is to discover 3D semantic information by grouping superpoints according to their global patterns in the frequency domain, thus generating highly accurate semantic pseudo-labels for training a segmentation network. Extensive experiments on two indoor and an outdoor datasets show that our LogoSP surpasses all existing unsupervised methods by large margins, achieving the state-of-the-art performance for unsupervised 3D semantic segmentation. Notably, our investigation into the learned global patterns reveals that they truly represent meaningful 3D semantics in the absence of human labels during training.
Authors: Ivan Alberico, Marco Cannici, Giovanni Cioffi, Davide Scaramuzza
Abstract: In this paper, we present a real-time egocentric trajectory prediction system for table tennis using event cameras. Unlike standard cameras, which suffer from high latency and motion blur at fast ball speeds, event cameras provide higher temporal resolution, allowing more frequent state updates, greater robustness to outliers, and accurate trajectory predictions using just a short time window after the opponent's impact. We collect a dataset of ping-pong game sequences, including 3D ground-truth trajectories of the ball, synchronized with sensor data from the Meta Project Aria glasses and event streams. Our system leverages foveated vision, using eye-gaze data from the glasses to process only events in the viewer's fovea. This biologically inspired approach improves ball detection performance and significantly reduces computational latency, as it efficiently allocates resources to the most perceptually relevant regions, achieving a reduction factor of 10.81 on the collected trajectories. Our detection pipeline has a worst-case total latency of 4.5 ms, including computation and perception - significantly lower than a frame-based 30 FPS system, which, in the worst case, takes 66 ms solely for perception. Finally, we fit a trajectory prediction model to the estimated states of the ball, enabling 3D trajectory forecasting in the future. To the best of our knowledge, this is the first approach to predict table tennis trajectories from an egocentric perspective using event cameras.
Authors: Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva, Vladimir Arkhipkin, Denis Dimitrov
Abstract: Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to mitigating common artifacts in KL-VAE training without requiring radical architectural changes. We present a detailed taxonomy of five prevalent artifacts - color shift, grid patterns, blur, corner and droplet artifacts - and analyze their root causes. Through straightforward modifications, including adjustments to loss weights, padding strategies, and the integration of Spatially Conditional Normalization, we demonstrate significant improvements in VAE performance. Our method achieves state-of-the-art results in image reconstruction metrics (PSNR and SSIM) across multiple benchmarks and enhances text-to-image generation quality, as evidenced by superior CLIP scores. By preserving the simplicity of the KL-VAE framework while addressing its practical challenges, VIVAT offers actionable insights for researchers and practitioners aiming to optimize VAE training.
Authors: Jinxi Li, Ziyang Song, Siyuan Zhou, Bo Yang
Abstract: In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorporating physics simulation into neural networks, existing works often fail to learn complex physical motions at boundaries or require object priors such as masks or types. In this paper, we propose FreeGave to learn the physics of complex dynamic 3D scenes without needing any object priors. The key to our approach is to introduce a physics code followed by a carefully designed divergence-free module for estimating a per-Gaussian velocity field, without relying on the inefficient PINN losses. Extensive experiments on three public datasets and a newly collected challenging real-world dataset demonstrate the superior performance of our method for future frame extrapolation and motion segmentation. Most notably, our investigation into the learned physics codes reveals that they truly learn meaningful 3D physical motion patterns in the absence of any human labels in training.
Authors: Muhammad Ahmed Humais, Xiaoqian Huang, Hussain Sajwani, Sajid Javed, Yahya Zweiri
Abstract: Event cameras unlock new frontiers that were previously unthinkable with standard frame-based cameras. One notable example is low-latency motion estimation (optical flow), which is critical for many real-time applications. In such applications, the computational efficiency of algorithms is paramount. Although recent deep learning paradigms such as CNN, RNN, or ViT have shown remarkable performance, they often lack the desired computational efficiency. Conversely, asynchronous event-based methods including SNNs and GNNs are computationally efficient; however, these approaches fail to capture sufficient spatio-temporal information, a powerful feature required to achieve better performance for optical flow estimation. In this work, we introduce Spatio-Temporal State Space Model (STSSM) module along with a novel network architecture to develop an extremely efficient solution with competitive performance. Our STSSM module leverages state-space models to effectively capture spatio-temporal correlations in event data, offering higher performance with lower complexity compared to ViT, CNN-based architectures in similar settings. Our model achieves 4.5x faster inference and 8x lower computations compared to TMA and 2x lower computations compared to EV-FlowNet with competitive performance on the DSEC benchmark. Our code will be available at https://github.com/AhmedHumais/E-STMFlow
Authors: Zubin Bhuyan, Yuanchang Xie, AngkeaReach Rith, Xintong Yan, Nasko Apostolov, Jimi Oke, Chengbo Ai
Abstract: With the increasing availability of aerial and satellite imagery, deep learning presents significant potential for transportation asset management, safety analysis, and urban planning. This study introduces CrosswalkNet, a robust and efficient deep learning framework designed to detect various types of pedestrian crosswalks from 15-cm resolution aerial images. CrosswalkNet incorporates a novel detection approach that improves upon traditional object detection strategies by utilizing oriented bounding boxes (OBB), enhancing detection precision by accurately capturing crosswalks regardless of their orientation. Several optimization techniques, including Convolutional Block Attention, a dual-branch Spatial Pyramid Pooling-Fast module, and cosine annealing, are implemented to maximize performance and efficiency. A comprehensive dataset comprising over 23,000 annotated crosswalk instances is utilized to train and validate the proposed framework. The best-performing model achieves an impressive precision of 96.5% and a recall of 93.3% on aerial imagery from Massachusetts, demonstrating its accuracy and effectiveness. CrosswalkNet has also been successfully applied to datasets from New Hampshire, Virginia, and Maine without transfer learning or fine-tuning, showcasing its robustness and strong generalization capability. Additionally, the crosswalk detection results, processed using High-Performance Computing (HPC) platforms and provided in polygon shapefile format, have been shown to accelerate data processing and detection, supporting real-time analysis for safety and mobility applications. This integration offers policymakers, transportation engineers, and urban planners an effective instrument to enhance pedestrian safety and improve urban mobility.
Authors: Gen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao, Marc Pollefeys, Siyu Tang
Abstract: Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction. These capabilities enable systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video. EgoM2P also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/
Authors: Simone Facchiano, Stefano Saravalle, Matteo Migliarini, Edoardo De Matteis, Alessio Sampieri, Andrea Pilzer, Emanuele Rodol\`a, Indro Spinelli, Luca Franco, Fabio Galasso
Abstract: Video generative models democratize the creation of visual content through intuitive instruction following, but they also inherit the biases and harmful concepts embedded within their web-scale training data. This inheritance creates a significant risk, as users can readily generate undesirable and even illegal content. This work introduces the first unlearning technique tailored explicitly for video diffusion models to address this critical issue. Our method requires 5 multi-modal prompt pairs only. Each pair contains a "safe" and an "unsafe" example that differ only by the target concept. Averaging their per-layer latent differences produces a "refusal vector", which, once subtracted from the model parameters, neutralizes the unsafe concept. We introduce a novel low-rank factorization approach on the covariance difference of embeddings that yields robust refusal vectors. This isolates the target concept while minimizing collateral unlearning of other semantics, thus preserving the visual quality of the generated video. Our method preserves the model's generation quality while operating without retraining or access to the original training data. By embedding the refusal direction directly into the model's weights, the suppression mechanism becomes inherently more robust against adversarial bypass attempts compared to surface-level input-output filters. In a thorough qualitative and quantitative evaluation, we show that we can neutralize a variety of harmful contents, including explicit nudity, graphic violence, copyrights, and trademarks. Project page: https://www.pinlab.org/video-unlearning.
Authors: Jie Yang, Feipeng Ma, Zitian Wang, Dacheng Yin, Kang Rong, Fengyun Rao, Ruimao Zhang
Abstract: Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL) training paradigms to multimodal large language models (MLLM), focusing on domain-specific tasks like math and visual perception, a critical question remains: How can we achieve the general-purpose visual-language reasoning through RL? To address this challenge, we make three key efforts: (1) A novel Scalable Multimodal QA Synthesis pipeline that autonomously generates context-aware, reasoning-centric question-answer (QA) pairs directly from the given images. (2) The open-source WeThink dataset containing over 120K multimodal QA pairs with annotated reasoning paths, curated from 18 diverse dataset sources and covering various question domains. (3) A comprehensive exploration of RL on our dataset, incorporating a hybrid reward mechanism that combines rule-based verification with model-based assessment to optimize RL training efficiency across various task domains. Across 14 diverse MLLM benchmarks, we demonstrate that our WeThink dataset significantly enhances performance, from mathematical reasoning to diverse general multimodal tasks. Moreover, we show that our automated data pipeline can continuously increase data diversity to further improve model performance.
Authors: Yaxita Amin, Naimisha S Trivedi, Rashmi Bhattad
Abstract: Remote sensing change detection is essential for monitoring the everchanging landscapes of the Earth. The U-Net architecture has gained popularity for its capability to capture spatial information and perform pixel-wise classification. However, their application in the Remote sensing field remains largely unexplored. Therefore, this paper fill the gap by conducting a comprehensive analysis of 34 papers. This study conducts a comparison and analysis of 18 different U-Net variations, assessing their potential for detecting changes in remote sensing. We evaluate both benefits along with drawbacks of each variation within the framework of this particular application. We emphasize variations that are explicitly built for change detection, such as Siamese Swin-U-Net, which utilizes a Siamese architecture. The analysis highlights the significance of aspects such as managing data from different time periods and collecting relationships over a long distance to enhance the precision of change detection. This study provides valuable insights for researchers and practitioners that choose U-Net versions for remote sensing change detection tasks.
Authors: Chengyue Huang, Yuchen Zhu, Sichen Zhu, Jingyun Xiao, Moises Andrade, Shivang Chopra, Zsolt Kira
Abstract: Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they often rely on shallow heuristics -- such as copying or majority voting -- rather than true task understanding. We revisit this assumption by evaluating VLMs under distribution shifts, where support examples come from a dataset different from the query. Surprisingly, performance often degrades with more demonstrations, and models tend to copy answers rather than learn from them. To investigate further, we propose a new MM-ICL with Reasoning pipeline that augments each demonstration with a generated rationale alongside the answer. We conduct extensive and comprehensive experiments on both perception- and reasoning-required datasets with open-source VLMs ranging from 3B to 72B and proprietary models such as Gemini 2.0. We conduct controlled studies varying shot count, retrieval method, rationale quality, and distribution. Our results show limited performance sensitivity across these factors, suggesting that current VLMs do not effectively utilize demonstration-level information as intended in MM-ICL.
Authors: Yizhen Li, Dell Zhang, Xuelong Li, Yiqing Shen
Abstract: Reasoning Segmentation (RS) is a multimodal vision-text task that requires segmenting objects based on implicit text queries, demanding both precise visual perception and vision-text reasoning capabilities. Current RS approaches rely on fine-tuning vision-language models (VLMs) for both perception and reasoning, but their tokenization of images fundamentally disrupts continuous spatial relationships between objects. We introduce DTwinSeger, a novel RS approach that leverages Digital Twin (DT) representation as an intermediate layer to decouple perception from reasoning. Innovatively, DTwinSeger reformulates RS as a two-stage process, where the first transforms the image into a structured DT representation that preserves spatial relationships and semantic properties and then employs a Large Language Model (LLM) to perform explicit reasoning over this representation to identify target objects. We propose a supervised fine-tuning method specifically for LLM with DT representation, together with a corresponding fine-tuning dataset Seg-DT, to enhance the LLM's reasoning capabilities with DT representations. Experiments show that our method can achieve state-of-the-art performance on two image RS benchmarks and three image referring segmentation benchmarks. It yields that DT representation functions as an effective bridge between vision and text, enabling complex multimodal reasoning tasks to be accomplished solely with an LLM.
Authors: Ari Vesalainen, Jenna Kanerva, Aida Nitsch, Kiia Korsu, Ilari Larkiola, Laura Ruotsalainen, Filip Ginter
Abstract: This article presents a large-scale effort to create a structured dataset of internal migration in Finland between 1800 and 1920 using digitized church moving records. These records, maintained by Evangelical-Lutheran parishes, document the migration of individuals and families and offer a valuable source for studying historical demographic patterns. The dataset includes over six million entries extracted from approximately 200,000 images of handwritten migration records. The data extraction process was automated using a deep learning pipeline that included layout analysis, table detection, cell classification, and handwriting recognition. The complete pipeline was applied to all images, resulting in a structured dataset suitable for research. The dataset can be used to study internal migration, urbanization, and family migration, and the spread of disease in preindustrial Finland. A case study from the Elim\"aki parish shows how local migration histories can be reconstructed. The work demonstrates how large volumes of handwritten archival material can be transformed into structured data to support historical and demographic research.
Authors: Wenxin Tang, Jingyu Xiao, Wenxuan Jiang, Xi Xiao, Yuhang Wang, Xuxin Tang, Qing Li, Yuehe Ma, Junliang Liu, Shisong Tang, Michael R. Lyu
Abstract: Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.
Authors: Ziyang Gong, Wenhao Li, Oliver Ma, Songyuan Li, Jiayi Ji, Xue Yang, Gen Luo, Junchi Yan, Rongrong Ji
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in various multimodal tasks. To pursue higher intelligence in space, MLLMs require integrating multiple atomic spatial capabilities to handle complex and dynamic tasks. However, existing benchmarks struggle to comprehensively evaluate the spatial intelligence of common MLLMs from the atomic level to the compositional level. To fill this gap, we present SpaCE-10, a comprehensive benchmark for compositional spatial evaluations. In SpaCE-10, we define 10 atomic spatial capabilities, which are combined to form 8 compositional capabilities. Based on these definitions, we propose a novel hierarchical annotation pipeline to generate high-quality and diverse question-answer (QA) pairs. With over 150+ hours of human expert effort, we obtain over 5k QA pairs for 811 real indoor scenes in SpaCE-10, which covers various evaluation settings like point cloud input and multi-choice QA. We conduct an extensive evaluation of common MLLMs on SpaCE-10 and find that even the most advanced MLLM still lags behind humans by large margins. Through our careful study, we also draw several significant findings that benefit the MLLM community. For example, we reveal that the shortcoming of counting capability greatly limits the compositional spatial capabilities of existing MLLMs. The evaluation code and benchmark datasets are available at https://github.com/Cuzyoung/SpaCE-10.
Authors: Jiahao Meng, Shuyang Sun, Yue Tan, Lu Qi, Yunhai Tong, Xiangtai Li, Longyin Wen
Abstract: Current Multimodal Large Language Models (MLLMs) may struggle with understanding long or complex videos due to computational demands at test time, lack of robustness, and limited accuracy, primarily stemming from their feed-forward processing nature. These limitations could be more severe for models with fewer parameters. To address these limitations, we propose a novel framework inspired by cybernetic principles, redesigning video MLLMs as adaptive systems capable of self-monitoring, self-correction, and dynamic resource allocation during inference. Our approach, CyberV, introduces a cybernetic loop consisting of an MLLM Inference System, a Sensor, and a Controller. Specifically, the sensor monitors forward processes of the MLLM and collects intermediate interpretations, such as attention drift, then the controller determines when and how to trigger self-correction and generate feedback to guide the next round. This test-time adaptive scaling framework enhances frozen MLLMs without requiring retraining or additional components. Experiments demonstrate significant improvements: CyberV boosts Qwen2.5-VL-7B by 8.3% and InternVL3-8B by 5.5% on VideoMMMU, surpassing the competitive proprietary model GPT-4o. When applied to Qwen2.5-VL-72B, it yields a 10.0% improvement, achieving performance even comparable to human experts. Furthermore, our method demonstrates consistent gains on general-purpose benchmarks, such as VideoMME and WorldSense, highlighting its effectiveness and generalization capabilities in making MLLMs more robust and accurate for dynamic video understanding. The code is released at https://github.com/marinero4972/CyberV.
Authors: Jingjing Chang, Yixiao Fang, Peng Xing, Shuhan Wu, Wei Cheng, Rui Wang, Xianfang Zeng, Gang Yu, Hai-Bao Chen
Abstract: Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations, for example, the evaluation on reasoning, text rendering and style. Notably, recent state-of-the-art models, with their rich knowledge modeling capabilities, show promising results on the image generation problems requiring strong reasoning ability, yet existing evaluation systems have not adequately addressed this frontier. To systematically address these gaps, we introduce OneIG-Bench, a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensions, including prompt-image alignment, text rendering precision, reasoning-generated content, stylization, and diversity. By structuring the evaluation, this benchmark enables in-depth analysis of model performance, helping researchers and practitioners pinpoint strengths and bottlenecks in the full pipeline of image generation. Specifically, OneIG-Bench enables flexible evaluation by allowing users to focus on a particular evaluation subset. Instead of generating images for the entire set of prompts, users can generate images only for the prompts associated with the selected dimension and complete the corresponding evaluation accordingly. Our codebase and dataset are now publicly available to facilitate reproducible evaluation studies and cross-model comparisons within the T2I research community.
Authors: Dmitrii Vorobev, Artem Prosvetov, Karim Elhadji Daou
Abstract: We propose a computationally efficient method for real-time three-dimensional football trajectory reconstruction from a single broadcast camera. In contrast to previous work, our approach introduces a multi-mode state model with $W$ discrete modes to significantly accelerate optimization while preserving centimeter-level accuracy -- even in cases of severe occlusion, motion blur, and complex backgrounds. The system operates on standard CPUs and achieves low latency suitable for live broadcast settings. Extensive evaluation on a proprietary dataset of 6K-resolution Russian Premier League matches demonstrates performance comparable to multi-camera systems, without the need for specialized or costly infrastructure. This work provides a practical method for accessible and accurate 3D ball tracking in professional football environments.
Authors: Mingquan Lin, Gregory Holste, Song Wang, Yiliang Zhou, Yishu Wei, Imon Banerjee, Pengyi Chen, Tianjie Dai, Yuexi Du, Nicha C. Dvornek, Yuyan Ge, Zuowei Guo, Shouhei Hanaoka, Dongkyun Kim, Pablo Messina, Yang Lu, Denis Parra, Donghyun Son, \'Alvaro Soto, Aisha Urooj, Ren\'e Vidal, Yosuke Yamagishi, Zefan Yang, Ruichi Zhang, Yang Zhou, Leo Anthony Celi, Ronald M. Summers, Zhiyong Lu, Hao Chen, Adam Flanders, George Shih, Zhangyang Wang, Yifan Peng
Abstract: The CXR-LT series is a community-driven initiative designed to enhance lung disease classification using chest X-rays (CXR). It tackles challenges in open long-tailed lung disease classification and enhances the measurability of state-of-the-art techniques. The first event, CXR-LT 2023, aimed to achieve these goals by providing high-quality benchmark CXR data for model development and conducting comprehensive evaluations to identify ongoing issues impacting lung disease classification performance. Building on the success of CXR-LT 2023, the CXR-LT 2024 expands the dataset to 377,110 chest X-rays (CXRs) and 45 disease labels, including 19 new rare disease findings. It also introduces a new focus on zero-shot learning to address limitations identified in the previous event. Specifically, CXR-LT 2024 features three tasks: (i) long-tailed classification on a large, noisy test set, (ii) long-tailed classification on a manually annotated "gold standard" subset, and (iii) zero-shot generalization to five previously unseen disease findings. This paper provides an overview of CXR-LT 2024, detailing the data curation process and consolidating state-of-the-art solutions, including the use of multimodal models for rare disease detection, advanced generative approaches to handle noisy labels, and zero-shot learning strategies for unseen diseases. Additionally, the expanded dataset enhances disease coverage to better represent real-world clinical settings, offering a valuable resource for future research. By synthesizing the insights and innovations of participating teams, we aim to advance the development of clinically realistic and generalizable diagnostic models for chest radiography.
Authors: Tuomas Oikarinen, Ge Yan, Akshay Kulkarni, Tsui-Wei Weng
Abstract: Interpreting individual neurons or directions in activations space is an important component of mechanistic interpretability. As such, many algorithms have been proposed to automatically produce neuron explanations, but it is often not clear how reliable these explanations are, or which methods produce the best explanations. This can be measured via crowd-sourced evaluations, but they can often be noisy and expensive, leading to unreliable results. In this paper, we carefully analyze the evaluation pipeline and develop a cost-effective and highly accurate crowdsourced evaluation strategy. In contrast to previous human studies that only rate whether the explanation matches the most highly activating inputs, we estimate whether the explanation describes neuron activations across all inputs. To estimate this effectively, we introduce a novel application of importance sampling to determine which inputs are the most valuable to show to raters, leading to around 30x cost reduction compared to uniform sampling. We also analyze the label noise present in crowd-sourced evaluations and propose a Bayesian method to aggregate multiple ratings leading to a further ~5x reduction in number of ratings required for the same accuracy. Finally, we use these methods to conduct a large-scale study comparing the quality of neuron explanations produced by the most popular methods for two different vision models.
Authors: Zhengyao Lv, Tianlin Pan, Chenyang Si, Zhaoxi Chen, Wangmeng Zuo, Ziwei Liu, Kwan-Yee K. Wong
Abstract: Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and generated content. We identify two key issues in the attention mechanism of MM-DiT, namely 1) the suppression of cross-modal attention due to token imbalance between visual and textual modalities and 2) the lack of timestep-aware attention weighting, which hinder the alignment. To address these issues, we propose \textbf{Temperature-Adjusted Cross-modal Attention (TACA)}, a parameter-efficient method that dynamically rebalances multimodal interactions through temperature scaling and timestep-dependent adjustment. When combined with LoRA fine-tuning, TACA significantly enhances text-image alignment on the T2I-CompBench benchmark with minimal computational overhead. We tested TACA on state-of-the-art models like FLUX and SD3.5, demonstrating its ability to improve image-text alignment in terms of object appearance, attribute binding, and spatial relationships. Our findings highlight the importance of balancing cross-modal attention in improving semantic fidelity in text-to-image diffusion models. Our codes are publicly available at \href{https://github.com/Vchitect/TACA}
Authors: Haoguang Lu, Jiacheng Chen, Zhenguo Yang, Aurele Tohokantche Gnanha, Fu Lee Wang, Li Qing, Xudong Mao
Abstract: Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing semantics are challenging to specify precisely using textual descriptions alone. A practical alternative involves learning editing semantics from paired source-target examples. Existing exemplar-based editing methods still rely on text prompts describing the change within paired examples or learning implicit text-based editing instructions. In this paper, we introduce PairEdit, a novel visual editing method designed to effectively learn complex editing semantics from a limited number of image pairs or even a single image pair, without using any textual guidance. We propose a target noise prediction that explicitly models semantic variations within paired images through a guidance direction term. Moreover, we introduce a content-preserving noise schedule to facilitate more effective semantic learning. We also propose optimizing distinct LoRAs to disentangle the learning of semantic variations from content. Extensive qualitative and quantitative evaluations demonstrate that PairEdit successfully learns intricate semantics while significantly improving content consistency compared to baseline methods. Code will be available at https://github.com/xudonmao/PairEdit.
Authors: Ming-Feng Li, Xin Yang, Fu-En Wang, Hritam Basak, Yuyin Sun, Shreekant Gayaka, Min Sun, Cheng-Hao Kuo
Abstract: 6D object pose estimation has shown strong generalizability to novel objects. However, existing methods often require either a complete, well-reconstructed 3D model or numerous reference images that fully cover the object. Estimating 6D poses from partial references, which capture only fragments of an object's appearance and geometry, remains challenging. To address this, we propose UA-Pose, an uncertainty-aware approach for 6D object pose estimation and online object completion specifically designed for partial references. We assume access to either (1) a limited set of RGBD images with known poses or (2) a single 2D image. For the first case, we initialize a partial object 3D model based on the provided images and poses, while for the second, we use image-to-3D techniques to generate an initial object 3D model. Our method integrates uncertainty into the incomplete 3D model, distinguishing between seen and unseen regions. This uncertainty enables confidence assessment in pose estimation and guides an uncertainty-aware sampling strategy for online object completion, enhancing robustness in pose estimation accuracy and improving object completeness. We evaluate our method on the YCB-Video, YCBInEOAT, and HO3D datasets, including RGBD sequences of YCB objects manipulated by robots and human hands. Experimental results demonstrate significant performance improvements over existing methods, particularly when object observations are incomplete or partially captured. Project page: https://minfenli.github.io/UA-Pose/
Authors: Junhao Chen, Yulia Tsvetkov, Xiaochuang Han
Abstract: Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware outputs, while diffusion models operate in continuous latent spaces to refine high-fidelity visual details. However, existing hybrids often lack systematic guidance on how and why to allocate model capacity between these paradigms. In this work, we introduce MADFormer, a Mixed Autoregressive and Diffusion Transformer that serves as a testbed for analyzing AR-diffusion trade-offs. MADFormer partitions image generation into spatial blocks, using AR layers for one-pass global conditioning across blocks and diffusion layers for iterative local refinement within each block. Through controlled experiments on FFHQ-1024 and ImageNet, we identify two key insights: (1) block-wise partitioning significantly improves performance on high-resolution images, and (2) vertically mixing AR and diffusion layers yields better quality-efficiency balances--improving FID by up to 75% under constrained inference compute. Our findings offer practical design principles for future hybrid generative models.
Authors: Aadarsh Sahoo, Vansh Tibrewal, Georgia Gkioxari
Abstract: Creating machines capable of understanding the world in 3D is essential in assisting designers that build and edit 3D environments and robots navigating and interacting within a three-dimensional space. Inspired by advances in language and image modeling, we investigate the potential of autoregressive models for a new modality: structured 3D scenes. To this end, we propose a unified LLM framework that aligns language, images, and 3D scenes and provide a detailed ''cookbook'' outlining critical design choices for achieving optimal training and performance addressing key questions related to data representation, modality-specific objectives, and more. We evaluate performance across four core 3D tasks -- rendering, recognition, instruction-following, and question-answering -- and four 3D datasets, synthetic and real-world. We extend our approach to reconstruct complex 3D object shapes by enriching our 3D modality with quantized shape encodings, and show our model's effectiveness on real-world 3D object recognition tasks. Project webpage: https://glab-caltech.github.io/kyvo/
Authors: Shuchen Weng, Haojie Zheng, Zheng Chang, Si Li, Boxin Shi, Xinlong Wang
Abstract: Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively -- resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment. Project page: https://hjzheng.net/projects/MTV/.
Authors: Hidir Yesiltepe, Pinar Yanardag
Abstract: In this work, we address dynamic view synthesis from monocular videos as an inverse problem in a training-free setting. By redesigning the noise initialization phase of a pre-trained video diffusion model, we enable high-fidelity dynamic view synthesis without any weight updates or auxiliary modules. We begin by identifying a fundamental obstacle to deterministic inversion arising from zero-terminal signal-to-noise ratio (SNR) schedules and resolve it by introducing a novel noise representation, termed K-order Recursive Noise Representation. We derive a closed form expression for this representation, enabling precise and efficient alignment between the VAE-encoded and the DDIM inverted latents. To synthesize newly visible regions resulting from camera motion, we introduce Stochastic Latent Modulation, which performs visibility aware sampling over the latent space to complete occluded regions. Comprehensive experiments demonstrate that dynamic view synthesis can be effectively performed through structured latent manipulation in the noise initialization phase.
Authors: Lei Lai, Zekai Yin, Eshed Ohn-Bar
Abstract: We introduce ZeroVO, a novel visual odometry (VO) algorithm that achieves zero-shot generalization across diverse cameras and environments, overcoming limitations in existing methods that depend on predefined or static camera calibration setups. Our approach incorporates three main innovations. First, we design a calibration-free, geometry-aware network structure capable of handling noise in estimated depth and camera parameters. Second, we introduce a language-based prior that infuses semantic information to enhance robust feature extraction and generalization to previously unseen domains. Third, we develop a flexible, semi-supervised training paradigm that iteratively adapts to new scenes using unlabeled data, further boosting the models' ability to generalize across diverse real-world scenarios. We analyze complex autonomous driving contexts, demonstrating over 30% improvement against prior methods on three standard benchmarks, KITTI, nuScenes, and Argoverse 2, as well as a newly introduced, high-fidelity synthetic dataset derived from Grand Theft Auto (GTA). By not requiring fine-tuning or camera calibration, our work broadens the applicability of VO, providing a versatile solution for real-world deployment at scale.
Authors: Sicheng Mo, Ziyang Leng, Leon Liu, Weizhen Wang, Honglin He, Bolei Zhou
Abstract: Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We propose Dreamland, a hybrid world generation framework combining the granular control of a physics-based simulator and the photorealistic content output of large-scale pretrained generative models. In particular, we design a layered world abstraction that encodes both pixel-level and object-level semantics and geometry as an intermediate representation to bridge the simulator and the generative model. This approach enhances controllability, minimizes adaptation cost through early alignment with real-world distributions, and supports off-the-shelf use of existing and future pretrained generative models. We further construct a D3Sim dataset to facilitate the training and evaluation of hybrid generation pipelines. Experiments demonstrate that Dreamland outperforms existing baselines with 50.8% improved image quality, 17.9% stronger controllability, and has great potential to enhance embodied agent training. Code and data will be made available.
Authors: Stephanie Fu, Tyler Bonnen, Devin Guillory, Trevor Darrell
Abstract: Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a direct readout of their visual encoders to understand their ability to integrate across these modalities. Across a series of vision-centric benchmarks (e.g., depth estimation, correspondence), we find that VLMs perform substantially worse than their visual encoders, dropping to near-chance performance. We investigate these results through a series of analyses across the entire VLM: namely 1) the degradation of vision representations, 2) brittleness to task prompt, and 3) the language model's role in solving the task. We find that the bottleneck in performing these vision-centric tasks lies in this third category; VLMs are not effectively using visual information easily accessible throughout the entire model, and they inherit the language priors present in the LLM. Our work helps diagnose the failure modes of open-source VLMs, and presents a series of evaluations useful for future investigations into visual understanding within VLMs.
Authors: Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, Eli Shechtman
Abstract: We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs during inference. Unlike prior methods that denoise future frames based on ground-truth context frames, Self Forcing conditions each frame's generation on previously self-generated outputs by performing autoregressive rollout with key-value (KV) caching during training. This strategy enables supervision through a holistic loss at the video level that directly evaluates the quality of the entire generated sequence, rather than relying solely on traditional frame-wise objectives. To ensure training efficiency, we employ a few-step diffusion model along with a stochastic gradient truncation strategy, effectively balancing computational cost and performance. We further introduce a rolling KV cache mechanism that enables efficient autoregressive video extrapolation. Extensive experiments demonstrate that our approach achieves real-time streaming video generation with sub-second latency on a single GPU, while matching or even surpassing the generation quality of significantly slower and non-causal diffusion models. Project website: http://self-forcing.github.io/
Authors: Nick Jiang, Amil Dravid, Alexei Efros, Yossi Gandelsman
Abstract: We investigate the mechanism underlying a previously identified phenomenon in Vision Transformers -- the emergence of high-norm tokens that lead to noisy attention maps. We observe that in multiple models (e.g., CLIP, DINOv2), a sparse set of neurons is responsible for concentrating high-norm activations on outlier tokens, leading to irregular attention patterns and degrading downstream visual processing. While the existing solution for removing these outliers involves retraining models from scratch with additional learned register tokens, we use our findings to create a training-free approach to mitigate these artifacts. By shifting the high-norm activations from our discovered register neurons into an additional untrained token, we can mimic the effect of register tokens on a model already trained without registers. We demonstrate that our method produces cleaner attention and feature maps, enhances performance over base models across multiple downstream visual tasks, and achieves results comparable to models explicitly trained with register tokens. We then extend test-time registers to off-the-shelf vision-language models to improve their interpretability. Our results suggest that test-time registers effectively take on the role of register tokens at test-time, offering a training-free solution for any pre-trained model released without them.
Authors: Yunfei Xie, Yinsong Ma, Shiyi Lan, Alan Yuille, Junfei Xiao, Chen Wei
Abstract: Developing generalizable reasoning capabilities in multimodal large language models (MLLMs) remains challenging. Motivated by cognitive science literature suggesting that gameplay promotes transferable cognitive skills, we propose a novel post-training paradigm, Visual Game Learning, or ViGaL, where MLLMs develop out-of-domain generalization of multimodal reasoning through playing arcade-like games. Specifically, we show that post-training a 7B-parameter MLLM via reinforcement learning (RL) on simple arcade-like games, e.g. Snake, significantly enhances its downstream performance on multimodal math benchmarks like MathVista, and on multi-discipline questions like MMMU, without seeing any worked solutions, equations, or diagrams during RL, suggesting the capture of transferable reasoning skills. Remarkably, our model outperforms specialist models tuned on multimodal reasoning data in multimodal reasoning benchmarks, while preserving the base model's performance on general visual benchmarks, a challenge where specialist models often fall short. Our findings suggest a new post-training paradigm: synthetic, rule-based games can serve as controllable and scalable pre-text tasks that unlock generalizable multimodal reasoning abilities in MLLMs.
Authors: Anh-Quan Cao, Ivan Lopes, Raoul de Charette
Abstract: Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend the partial learning setup to a zero-shot setting, training a multi-task model on multiple synthetic datasets, each labeled for only a subset of tasks. Our method, StableMTL, repurposes image generators for latent regression. Adapting a denoising framework with task encoding, per-task conditioning and a tailored training scheme. Instead of per-task losses requiring careful balancing, a unified latent loss is adopted, enabling seamless scaling to more tasks. To encourage inter-task synergy, we introduce a multi-stream model with a task-attention mechanism that converts N-to-N task interactions into efficient 1-to-N attention, promoting effective cross-task sharing. StableMTL outperforms baselines on 7 tasks across 8 benchmarks.
Authors: Zhen Xu, Zhengqin Li, Zhao Dong, Xiaowei Zhou, Richard Newcombe, Zhaoyang Lv
Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We proposed a novel density control strategy in training, which enables our 4DGT to handle longer space-time input and remain efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can outperform prior Gaussian-based networks significantly in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos. Project page: https://4dgt.github.io
URLs: https://4dgt.github.io
Authors: Mingyu Lu, Ethan Weinberger, Chanwoo Kim, Su-In Lee
Abstract: High-content screening (HCS) assays based on high-throughput microscopy techniques such as Cell Painting have enabled the interrogation of cells' morphological responses to perturbations at an unprecedented scale. The collection of such data promises to facilitate a better understanding of the relationships between different perturbations and their effects on cellular state. Towards achieving this goal, recent advances in cross-modal contrastive learning could, in theory, be leveraged to learn a unified latent space that aligns perturbations with their corresponding morphological effects. However, the application of such methods to HCS data is not straightforward due to substantial differences in the semantics of Cell Painting images compared to natural images, and the difficulty of representing different classes of perturbations (e.g., small molecule vs CRISPR gene knockout) in a single latent space. In response to these challenges, here we introduce CellCLIP, a cross-modal contrastive learning framework for HCS data. CellCLIP leverages pre-trained image encoders coupled with a novel channel encoding scheme to better capture relationships between different microscopy channels in image embeddings, along with natural language encoders for representing perturbations. Our framework outperforms current open-source models, demonstrating the best performance in both cross-modal retrieval and biologically meaningful downstream tasks while also achieving significant reductions in computation time.
Authors: Ali Abedi, Charlene H. Chu, Shehroz S. Khan
Abstract: Agitation is one of the most common responsive behaviors in people living with dementia, particularly among those residing in community settings without continuous clinical supervision. Timely prediction of agitation can enable early intervention, reduce caregiver burden, and improve the quality of life for both patients and caregivers. This study aimed to develop and benchmark machine learning approaches for the early prediction of agitation in community-dwelling older adults with dementia using multimodal sensor data. A new set of agitation-related contextual features derived from activity data was introduced and employed for agitation prediction. A wide range of machine learning and deep learning models was evaluated across multiple problem formulations, including binary classification for single-timestamp tabular sensor data and multi-timestamp sequential sensor data, as well as anomaly detection for single-timestamp tabular sensor data. The study utilized the Technology Integrated Health Management (TIHM) dataset, the largest publicly available dataset for remote monitoring of people living with dementia, comprising 2,803 days of in-home activity, physiology, and sleep data. The most effective setting involved binary classification of sensor data using the current 6-hour timestamp to predict agitation at the subsequent timestamp. Incorporating additional information, such as time of day and agitation history, further improved model performance, with the highest AUC-ROC of 0.9720 and AUC-PR of 0.4320 achieved by the light gradient boosting machine. This work presents the first comprehensive benchmarking of state-of-the-art techniques for agitation prediction in community-based dementia care using privacy-preserving sensor data. The approach enables accurate, explainable, and efficient agitation prediction, supporting proactive dementia care and aging in place.
Authors: Masoud Rahimi, Reza Karbasi, Abdol-Hossein Vahabie
Abstract: We introduce an open-source Python framework for generating synthetic ECG image datasets to advance critical deep learning-based tasks in ECG analysis, including ECG digitization, lead region and lead name detection, and pixel-level waveform segmentation. Using the PTB-XL signal dataset, our proposed framework produces four open-access datasets: (1) ECG images in various lead configurations paired with time-series signals for ECG digitization, (2) ECG images annotated with YOLO-format bounding boxes for detection of lead region and lead name, (3)-(4) cropped single-lead images with segmentation masks compatible with U-Net-based models in normal and overlapping versions. In the overlapping case, waveforms from neighboring leads are superimposed onto the target lead image, while the segmentation masks remain clean. The open-source Python framework and datasets are publicly available at https://github.com/rezakarbasi/ecg-image-and-signal-dataset and https://doi.org/10.5281/zenodo.15484519, respectively.
URLs: https://github.com/rezakarbasi/ecg-image-and-signal-dataset, https://doi.org/10.5281/zenodo.15484519,
Authors: Thien Nhan Vo, Thanh Xuan Truong
Abstract: This study addresses the classification of heartbeats from ECG signals through two distinct approaches: traditional machine learning utilizing hand-crafted features and deep learning via transformed images of ECG beats. The dataset underwent preprocessing steps, including downsampling, filtering, and normalization, to ensure consistency and relevance for subsequent analysis. In the first approach, features such as heart rate variability (HRV), mean, variance, and RR intervals were extracted to train various classifiers, including SVM, Random Forest, AdaBoost, LSTM, Bi-directional LSTM, and LightGBM. The second approach involved transforming ECG signals into images using Gramian Angular Field (GAF), Markov Transition Field (MTF), and Recurrence Plots (RP), with these images subsequently classified using CNN architectures like VGG and Inception. Experimental results demonstrate that the LightGBM model achieved the highest performance, with an accuracy of 99% and an F1 score of 0.94, outperforming the image-based CNN approach (F1 score of 0.85). Models such as SVM and AdaBoost yielded significantly lower scores, indicating limited suitability for this task. The findings underscore the superior ability of hand-crafted features to capture temporal and morphological variations in ECG signals compared to image-based representations of individual beats. Future investigations may benefit from incorporating multi-lead ECG signals and temporal dependencies across successive beats to enhance classification accuracy further.
Authors: Lingyao Li, Dawei Li, Zhenhui Ou, Xiaoran Xu, Jingxiao Liu, Zihui Ma, Runlong Yu, Min Deng
Abstract: Efficient simulation is essential for enhancing proactive preparedness for sudden-onset disasters such as earthquakes. Recent advancements in large language models (LLMs) as world models show promise in simulating complex scenarios. This study examines multiple LLMs to proactively estimate perceived earthquake impacts. Leveraging multimodal datasets including geospatial, socioeconomic, building, and street-level imagery data, our framework generates Modified Mercalli Intensity (MMI) predictions at zip code and county scales. Evaluations on the 2014 Napa and 2019 Ridgecrest earthquakes using USGS ''Did You Feel It? (DYFI)'' reports demonstrate significant alignment, as evidenced by a high correlation of 0.88 and a low RMSE of 0.77 as compared to real reports at the zip code level. Techniques such as RAG and ICL can improve simulation performance, while visual inputs notably enhance accuracy compared to structured numerical data alone. These findings show the promise of LLMs in simulating disaster impacts that can help strengthen pre-event planning.
Authors: Yash Turkar, Youngjin Kim, Karthik Dantu
Abstract: Subterranean environments such as culverts present significant challenges to robot vision due to dim lighting and lack of distinctive features. Although onboard illumination can help, it introduces issues such as specular reflections, overexposure, and increased power consumption. We propose NightHawk, a framework that combines active illumination with exposure control to optimize image quality in these settings. NightHawk formulates an online Bayesian optimization problem to determine the best light intensity and exposure-time for a given scene. We propose a novel feature detector-based metric to quantify image utility and use it as the cost function for the optimizer. We built NightHawk as an event-triggered recursive optimization pipeline and deployed it on a legged robot navigating a culvert beneath the Erie Canal. Results from field experiments demonstrate improvements in feature detection and matching by 47-197% enabling more reliable visual estimation in challenging lighting conditions.
Authors: Changsheng Fang, Yongtong Liu, Bahareh Morovati, Shuo Han, Yu Shi, Li Zhou, Shuyi Fan, Hengyong Yu
Abstract: Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting ill-posed inverse problem poses significant challenges for accurate image reconstruction. Although deep learning and diffusion-based methods have shown promising results, they often lack physical interpretability or suffer from high computational costs due to iterative sampling starting from random noise. Recent advances in generative modeling, particularly Poisson Flow Generative Models (PFGM), enable high-fidelity image synthesis by modeling the full data distribution. In this work, we propose Residual Poisson Flow (ResPF) Generative Models for efficient and accurate sparse-view CT reconstruction. Based on PFGM++, ResPF integrates conditional guidance from sparse measurements and employs a hijacking strategy to significantly reduce sampling cost by skipping redundant initial steps. However, skipping early stages can degrade reconstruction quality and introduce unrealistic structures. To address this, we embed a data-consistency into each iteration, ensuring fidelity to sparse-view measurements. Yet, PFGM sampling relies on a fixed ordinary differential equation (ODE) trajectory induced by electrostatic fields, which can be disrupted by step-wise data consistency, resulting in unstable or degraded reconstructions. Inspired by ResNet, we introduce a residual fusion module to linearly combine generative outputs with data-consistent reconstructions, effectively preserving trajectory continuity. To the best of our knowledge, this is the first application of Poisson flow models to sparse-view CT. Extensive experiments on synthetic and clinical datasets demonstrate that ResPF achieves superior reconstruction quality, faster inference, and stronger robustness compared to state-of-the-art iterative, learning-based, and diffusion models.
Authors: Junming Wang, Yi Shi
Abstract: Discovering novel classes in open-world settings is crucial for real-world applications. Traditional explicit representations, such as object descriptors or 3D segmentation maps, are constrained by their discrete, hole-prone, and noisy nature, which hinders accurate novel class discovery. To address these challenges, we introduce NeurNCD, the first versatile and data-efficient framework for novel class discovery that employs the meticulously designed Embedding-NeRF model combined with KL divergence as a substitute for traditional explicit 3D segmentation maps to aggregate semantic embedding and entropy in visual embedding space. NeurNCD also integrates several key components, including feature query, feature modulation and clustering, facilitating efficient feature augmentation and information exchange between the pre-trained semantic segmentation network and implicit neural representations. As a result, our framework achieves superior segmentation performance in both open and closed-world settings without relying on densely labelled datasets for supervised training or human interaction to generate sparse label supervision. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches on the NYUv2 and Replica datasets.
Authors: Chuhao Chen, Zhiyang Dou, Chen Wang, Yiming Huang, Anjun Chen, Qiao Feng, Jiatao Gu, Lingjie Liu
Abstract: Faithfully reconstructing textured shapes and physical properties from videos presents an intriguing yet challenging problem. Significant efforts have been dedicated to advancing such a system identification problem in this area. Previous methods often rely on heavy optimization pipelines with a differentiable simulator and renderer to estimate physical parameters. However, these approaches frequently necessitate extensive hyperparameter tuning for each scene and involve a costly optimization process, which limits both their practicality and generalizability. In this work, we propose a novel framework, Vid2Sim, a generalizable video-based approach for recovering geometry and physical properties through a mesh-free reduced simulation based on Linear Blend Skinning (LBS), offering high computational efficiency and versatile representation capability. Specifically, Vid2Sim first reconstructs the observed configuration of the physical system from video using a feed-forward neural network trained to capture physical world knowledge. A lightweight optimization pipeline then refines the estimated appearance, geometry, and physical properties to closely align with video observations within just a few minutes. Additionally, after the reconstruction, Vid2Sim enables high-quality, mesh-free simulation with high efficiency. Extensive experiments demonstrate that our method achieves superior accuracy and efficiency in reconstructing geometry and physical properties from video data.
Authors: Nicol\'as Violante, Andreas Meuleman, Alban Gauthier, Fr\'edo Durand, Thibault Groueix, George Drettakis
Abstract: We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthesis but renderings of unseen and occluded parts remain low-quality if the training views are not exhaustive enough. Our key observation is that our environment is often full of repetitive elements. We propose to leverage those repetitions to improve the reconstruction of low-quality parts of the scene due to poor coverage and occlusions. We propose a method that segments each repeated instance in a 3DGS reconstruction, registers them together, and allows information to be shared among instances. Our method improves the geometry while also accounting for appearance variations across instances. We demonstrate our method on a variety of synthetic and real scenes with typical repetitive elements, leading to a substantial improvement in the quality of novel view synthesis.
Authors: Everett Richards, Bipul Thapa, Lena Mashayekhy
Abstract: Accurate and reliable object detection is critical for ensuring the safety and efficiency of Connected Autonomous Vehicles (CAVs). Traditional on-board perception systems have limited accuracy due to occlusions and blind spots, while cloud-based solutions introduce significant latency, making them unsuitable for real-time processing demands required for autonomous driving in dynamic environments. To address these challenges, we introduce an innovative framework, Edge-Enabled Collaborative Object Detection (ECOD) for CAVs, that leverages edge computing and multi-CAV collaboration for real-time, multi-perspective object detection. Our ECOD framework integrates two key algorithms: Perceptive Aggregation and Collaborative Estimation (PACE) and Variable Object Tally and Evaluation (VOTE). PACE aggregates detection data from multiple CAVs on an edge server to enhance perception in scenarios where individual CAVs have limited visibility. VOTE utilizes a consensus-based voting mechanism to improve the accuracy of object classification by integrating data from multiple CAVs. Both algorithms are designed at the edge to operate in real-time, ensuring low-latency and reliable decision-making for CAVs. We develop a hardware-based controlled testbed consisting of camera-equipped robotic CAVs and an edge server to evaluate the efficacy of our framework. Our experimental results demonstrate the significant benefits of ECOD in terms of improved object classification accuracy, outperforming traditional single-perspective onboard approaches by up to 75%, while ensuring low-latency, edge-driven real-time processing. This research highlights the potential of edge computing to enhance collaborative perception for latency-sensitive autonomous systems.
Authors: Yao Ni, Song Wen, Piotr Koniusz, Anoop Cherian
Abstract: Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suffer from two key issues: underfitting, where the model fails to reliably capture subject identity, and overfitting, where it memorizes the subject image and reduces background diversity. To address these challenges, we propose two auxiliary consistency losses for diffusion fine-tuning. First, a prior consistency regularization loss ensures that the predicted diffusion noise for prior (non-subject) images remains consistent with that of the pretrained model, improving fidelity. Second, a subject consistency regularization loss enhances the fine-tuned model's robustness to multiplicative noise modulated latent code, helping to preserve subject identity while improving diversity. Our experimental results demonstrate that incorporating these losses into fine-tuning not only preserves subject identity but also enhances image diversity, outperforming DreamBooth in terms of CLIP scores, background variation, and overall visual quality.
Authors: Chi-Sheng Chen
Abstract: Recent advancements in quantum machine learning have shown promise in enhancing classical neural network architectures, particularly in domains involving complex, high-dimensional data. Building upon prior work in temporal sequence modeling, this paper introduces Vision-QRWKV, a hybrid quantum-classical extension of the Receptance Weighted Key Value (RWKV) architecture, applied for the first time to image classification tasks. By integrating a variational quantum circuit (VQC) into the channel mixing component of RWKV, our model aims to improve nonlinear feature transformation and enhance the expressive capacity of visual representations. We evaluate both classical and quantum RWKV models on a diverse collection of 14 medical and standard image classification benchmarks, including MedMNIST datasets, MNIST, and FashionMNIST. Our results demonstrate that the quantum-enhanced model outperforms its classical counterpart on a majority of datasets, particularly those with subtle or noisy class distinctions (e.g., ChestMNIST, RetinaMNIST, BloodMNIST). This study represents the first systematic application of quantum-enhanced RWKV in the visual domain, offering insights into the architectural trade-offs and future potential of quantum models for lightweight and efficient vision tasks.
Authors: Olimjon Toirov, Wei Yu
Abstract: Non-Intrusive Load Monitoring (NILM) identifies the operating status and energy consumption of each electrical device in the circuit by analyzing the electrical signals at the bus, which is of great significance for smart power management. However, the complex and changeable load combinations and application environments lead to the challenges of poor feature robustness and insufficient model generalization of traditional NILM methods. To this end, this paper proposes a new non-intrusive load monitoring method that integrates "image load signature" and continual learning. This method converts multi-dimensional power signals such as current, voltage, and power factor into visual image load feature signatures, and combines deep convolutional neural networks to realize the identification and classification of multiple devices; at the same time, self-supervised pre-training is introduced to improve feature generalization, and continual online learning strategies are used to overcome model forgetting to adapt to the emergence of new loads. This paper conducts a large number of experiments on high-sampling rate load datasets, and compares a variety of existing methods and model variants. The results show that the proposed method has achieved significant improvements in recognition accuracy.
Authors: Wenhao Yao, Zhenxin Li, Shiyi Lan, Zi Wang, Xinglong Sun, Jose M. Alvarez, Zuxuan Wu
Abstract: In complex driving environments, autonomous vehicles must navigate safely. Relying on a single predicted path, as in regression-based approaches, usually does not explicitly assess the safety of the predicted trajectory. Selection-based methods address this by generating and scoring multiple trajectory candidates and predicting the safety score for each, but face optimization challenges in precisely selecting the best option from thousands of possibilities and distinguishing subtle but safety-critical differences, especially in rare or underrepresented scenarios. We propose DriveSuprim to overcome these challenges and advance the selection-based paradigm through a coarse-to-fine paradigm for progressive candidate filtering, a rotation-based augmentation method to improve robustness in out-of-distribution scenarios, and a self-distillation framework to stabilize training. DriveSuprim achieves state-of-the-art performance, reaching 93.5% PDMS in NAVSIM v1 and 87.1% EPDMS in NAVSIM v2 without extra data, demonstrating superior safetycritical capabilities, including collision avoidance and compliance with rules, while maintaining high trajectory quality in various driving scenarios.
Authors: Zhenxin Li, Wenhao Yao, Zi Wang, Xinglong Sun, Joshua Chen, Nadine Chang, Maying Shen, Zuxuan Wu, Shiyi Lan, Jose M. Alvarez
Abstract: End-to-end multi-modal planning is a promising paradigm in autonomous driving, enabling decision-making with diverse trajectory candidates. A key component is a robust trajectory scorer capable of selecting the optimal trajectory from these candidates. While recent trajectory scorers focus on scoring either large sets of static trajectories or small sets of dynamically generated ones, both approaches face significant limitations in generalization. Static vocabularies provide effective coarse discretization but struggle to make fine-grained adaptation, while dynamic proposals offer detailed precision but fail to capture broader trajectory distributions. To overcome these challenges, we propose GTRS (Generalized Trajectory Scoring), a unified framework for end-to-end multi-modal planning that combines coarse and fine-grained trajectory evaluation. GTRS consists of three complementary innovations: (1) a diffusion-based trajectory generator that produces diverse fine-grained proposals; (2) a vocabulary generalization technique that trains a scorer on super-dense trajectory sets with dropout regularization, enabling its robust inference on smaller subsets; and (3) a sensor augmentation strategy that enhances out-of-domain generalization while incorporating refinement training for critical trajectory discrimination. As the winning solution of the Navsim v2 Challenge, GTRS demonstrates superior performance even with sub-optimal sensor inputs, approaching privileged methods that rely on ground-truth perception. Code will be available at https://github.com/NVlabs/GTRS.
Authors: Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, Si Liu
Abstract: Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive System 1 policies, underutilizing VLMs' strengths in semantic reasoning and long-horizon planning. These System 2 capabilities-characterized by deliberative, goal-directed thinking-remain under explored due to the limited temporal scale and structural complexity of current benchmarks. To address this gap, we introduce RoboCerebra, a benchmark for evaluating high-level reasoning in long-horizon robotic manipulation. RoboCerebra includes: (1) a large-scale simulation dataset with extended task horizons and diverse subtask sequences in household environments; (2) a hierarchical framework combining a high-level VLM planner with a low-level vision-language-action (VLA) controller; and (3) an evaluation protocol targeting planning, reflection, and memory through structured System 1-System 2 interaction. The dataset is constructed via a top-down pipeline, where GPT generates task instructions and decomposes them into subtask sequences. Human operators execute the subtasks in simulation, yielding high-quality trajectories with dynamic object variations. Compared to prior benchmarks, RoboCerebra features significantly longer action sequences and denser annotations. We further benchmark state-of-the-art VLMs as System 2 modules and analyze their performance across key cognitive dimensions, advancing the development of more capable and generalizable robotic planners.
Authors: Hao Wang, Chengkai Hou, Xianglong Li, Yankai Fu, Chenxuan Li, Ning Chen, Gaole Dai, Jiaming Liu, Tiejun Huang, Shanghang Zhang
Abstract: Learning to control high-speed objects in the real world remains a challenging frontier in robotics. Table tennis serves as an ideal testbed for this problem, demanding both rapid interception of fast-moving balls and precise adjustment of their trajectories. This task presents two fundamental challenges: it requires a high-precision vision system capable of accurately predicting ball trajectories, and it necessitates intelligent strategic planning to ensure precise ball placement to target regions. The dynamic nature of table tennis, coupled with its real-time response requirements, makes it particularly well-suited for advancing robotic control capabilities in fast-paced, precision-critical domains. In this paper, we present SpikePingpong, a novel system that integrates spike-based vision with imitation learning for high-precision robotic table tennis. Our approach introduces two key attempts that directly address the aforementioned challenges: SONIC, a spike camera-based module that achieves millimeter-level precision in ball-racket contact prediction by compensating for real-world uncertainties such as air resistance and friction; and IMPACT, a strategic planning module that enables accurate ball placement to targeted table regions. The system harnesses a 20 kHz spike camera for high-temporal resolution ball tracking, combined with efficient neural network models for real-time trajectory correction and stroke planning. Experimental results demonstrate that SpikePingpong achieves a remarkable 91% success rate for 30 cm accuracy target area and 71% in the more challenging 20 cm accuracy task, surpassing previous state-of-the-art approaches by 38% and 37% respectively. These significant performance improvements enable the robust implementation of sophisticated tactical gameplay strategies, providing a new research perspective for robotic control in high-speed dynamic tasks.
Authors: Yitao Liu, Chenglei Si, Karthik Narasimhan, Shunyu Yao
Abstract: Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in these complex tasks. Moreover, current LLM agents are not designed to continually learn from past experiences during inference time, which could be crucial for them to gain these environment-specific experiences. To address this, we propose Contextual Experience Replay (CER), a training-free framework to enable efficient self-improvement for language agents in their context window. Specifically, CER accumulates and synthesizes past experiences into a dynamic memory buffer. These experiences encompass environment dynamics and common decision-making patterns, allowing the agents to retrieve and augment themselves with relevant knowledge in new tasks, enhancing their adaptability in complex environments. We evaluate CER on the challenging WebArena and VisualWebArena benchmarks. On VisualWebArena, CER achieves a competitive performance of 31.9%. On WebArena, CER also gets a competitive average success rate of 36.7%, relatively improving the success rate of the GPT-4o agent baseline by 51.0%. We also conduct a comprehensive analysis on it to prove its efficiency, validity and understand it better.
Authors: Can Li, Ting Zhang, Mei Wang, Hua Huang
Abstract: Large Multimodal Models (LMMs) have demonstrated remarkable problem-solving capabilities across various domains. However, their ability to perform mathematical reasoning when answer options are represented as images--an essential aspect of multi-image comprehension--remains underexplored. To bridge this gap, we introduce VisioMath, a benchmark designed to evaluate mathematical reasoning in multimodal contexts involving image-based answer choices. VisioMath comprises 8,070 images and 1,800 multiple-choice questions, where each answer option is an image, presenting unique challenges to existing LMMs. To the best of our knowledge, VisioMath is the first dataset specifically tailored for mathematical reasoning in image-based-option scenarios, where fine-grained distinctions between answer choices are critical for accurate problem-solving. We systematically evaluate state-of-the-art LMMs on VisioMath and find that even the most advanced models struggle with this task. Notably, GPT-4o achieves only 45.9% accuracy, underscoring the limitations of current models in reasoning over visually similar answer choices. By addressing a crucial gap in existing benchmarks, VisioMath establishes a rigorous testbed for future research, driving advancements in multimodal reasoning.
Authors: Adri\`a Molina Rodr\'iguez, Oriol Ramos Terrades, Josep Llad\'os
Abstract: Achieving robustness in recognition systems across diverse domains is crucial for their practical utility. While ample data availability is usually assumed, low-resource languages, such as ancient manuscripts and non-western languages, tend to be kept out of the equations of massive pretraining and foundational techniques due to an under representation. In this work, we aim for building models which can generalize to new distributions of data, such as alphabets, faster than centralized fine-tune strategies. For doing so, we take advantage of the recent advancements in model editing to enhance the incorporation of unseen scripts (low-resource learning). In contrast to state-of-the-art meta-learning, we showcase the effectiveness of domain merging in sparse distributions of data, with agnosticity of its relation to the overall distribution or any other prototyping necessity. Even when using the same exact training data, our experiments showcase significant performance boosts in \textbf{transfer learning} to new alphabets and \textbf{out-of-domain evaluation} in challenging domain shifts, including historical ciphered texts and non-Latin scripts. This research contributes a novel approach into building models that can easily adopt under-represented alphabets and, therefore, enable document recognition to a wider set of contexts and cultures.
Authors: Qinting Jiang, Chuyang Ye, Dongyan Wei, Bingli Wang, Yuan Xue, Jingyan Jiang, Zhi Wang
Abstract: Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for applications. Existing test-time adaptation (TTA) methods are challenged by dynamic, multiple test distributions within batches. We observe that feature distributions across different domains inherently cluster into distinct groups with varying means and variances. This divergence reveals a critical limitation of previous global normalization strategies in TTA, which inevitably distort the original data characteristics. Based on this insight, we propose Feature-based Instance Neighbor Discovery (FIND), which comprises three key components: Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN) and Selective FABN (S-FABN). LFD stably captures features with similar distributions at each layer by constructing graph structures. While FABN optimally combines source statistics with test-time distribution specific statistics for robust feature representation. Finally, S-FABN determines which layers require feature partitioning and which can remain unified, thereby enhancing inference efficiency. Extensive experiments demonstrate that FIND significantly outperforms existing methods, achieving a 30\% accuracy improvement in dynamic scenarios while maintaining computational efficiency.
Authors: Chenguang Huang, Oier Mees, Andy Zeng, Wolfram Burgard
Abstract: Grounding language to a navigating agent's observations can leverage pretrained multimodal foundation models to match perceptions to object or event descriptions. However, previous approaches remain disconnected from environment mapping, lack the spatial precision of geometric maps, or neglect additional modality information beyond vision. To address this, we propose multimodal spatial language maps as a spatial map representation that fuses pretrained multimodal features with a 3D reconstruction of the environment. We build these maps autonomously using standard exploration. We present two instances of our maps, which are visual-language maps (VLMaps) and their extension to audio-visual-language maps (AVLMaps) obtained by adding audio information. When combined with large language models (LLMs), VLMaps can (i) translate natural language commands into open-vocabulary spatial goals (e.g., "in between the sofa and TV") directly localized in the map, and (ii) be shared across different robot embodiments to generate tailored obstacle maps on demand. Building upon the capabilities above, AVLMaps extend VLMaps by introducing a unified 3D spatial representation integrating audio, visual, and language cues through the fusion of features from pretrained multimodal foundation models. This enables robots to ground multimodal goal queries (e.g., text, images, or audio snippets) to spatial locations for navigation. Additionally, the incorporation of diverse sensory inputs significantly enhances goal disambiguation in ambiguous environments. Experiments in simulation and real-world settings demonstrate that our multimodal spatial language maps enable zero-shot spatial and multimodal goal navigation and improve recall by 50% in ambiguous scenarios. These capabilities extend to mobile robots and tabletop manipulators, supporting navigation and interaction guided by visual, audio, and spatial cues.
Authors: Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Abstract: In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle this issue, we propose employing Early Exit (EE) strategies in VLMs. However, training exit classifiers in VLMs is challenging, particularly with limited labeled training data. To address this, we introduce FREE, an adversarial training approach within a GAN-based framework. Here, each exit consists of a transformer layer and a classifier. The transformer layer is adversarially trained to produce feature representations similar to the final layer, while a feature classifier serves as the discriminator. Our method focuses on performing input-adaptive inference that increases inference speed with minimal drop in performance. Experimental results demonstrate the effectiveness of our approach in enhancing accuracy and model robustness by mitigating overthinking and the phenomenon of mid-crisis that we highlight. We experimentally validate that our method speeds up the inference process by more than 1.51x while retaining comparable performance. The source code is available at https://github.com/Div290/FREE.
Authors: Sumit Sharma, Gopi Raju Matta, Kaushik Mitra
Abstract: Single Photon Avalanche Diodes (SPADs) represent a cutting-edge imaging technology, capable of detecting individual photons with remarkable timing precision. Building on this sensitivity, Single Photon Cameras (SPCs) enable image capture at exceptionally high speeds under both low and high illumination. Enabling 3D reconstruction and radiance field recovery from such SPC data holds significant promise. However, the binary nature of SPC images leads to severe information loss, particularly in texture and color, making traditional 3D synthesis techniques ineffective. To address this challenge, we propose a modular two-stage framework that converts binary SPC images into high-quality colorized novel views. The first stage performs image-to-image (I2I) translation using generative models such as Pix2PixHD, converting binary SPC inputs into plausible RGB representations. The second stage employs 3D scene reconstruction techniques like Neural Radiance Fields (NeRF) or Gaussian Splatting (3DGS) to generate novel views. We validate our two-stage pipeline (Pix2PixHD + Nerf/3DGS) through extensive qualitative and quantitative experiments, demonstrating significant improvements in perceptual quality and geometric consistency over the alternative baseline.
Authors: Akash Gupta, Amos Storkey, Mirella Lapata
Abstract: Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, is inconsistent and does not always improve monotonically with increasing examples. We hypothesize that this occurs due to the LMM being overwhelmed by additional information present in the image embeddings, which is not required for the downstream task. To address this, we propose a meta-learning approach that provides an alternative for inducing few-shot capabilities in LMMs, using a fixed set of soft prompts that are distilled from task-relevant image features and can be adapted at test time using a few examples. To facilitate this distillation, we introduce an attention-mapper module that can be easily integrated with the popular LLaVA v1.5 architecture and is jointly learned with soft prompts, enabling task adaptation in LMMs under low-data regimes with just a few gradient steps. Evaluation on the VL-ICL Bench shows that our method consistently outperforms ICL and related prompt-tuning approaches, even under image perturbations, improving task induction and reasoning across visual question answering tasks.
Authors: Mahdi Salmani, Alireza Abdollahpoorrostam, Seyed-Mohsen Moosavi-Dezfooli
Abstract: Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of queries low, where each query involves sending an input to the model and observing its output. Most existing methods assume that all queries have equal cost. However, in practice, queries may incur asymmetric costs; for example, in content moderation systems, certain output classes may trigger additional review, enforcement, or penalties, making them more costly than others. While prior work has considered such asymmetric cost settings, effective algorithms for this scenario remain underdeveloped. In this paper, we propose a general framework for decision-based attacks under asymmetric query costs, which we refer to as asymmetric black-box attacks. We modify two core components of existing attacks: the search strategy and the gradient estimation process. Specifically, we propose Asymmetric Search (AS), a more conservative variant of binary search that reduces reliance on high-cost queries, and Asymmetric Gradient Estimation (AGREST), which shifts the sampling distribution to favor low-cost queries. We design efficient algorithms that minimize total attack cost by balancing different query types, in contrast to earlier methods such as stealthy attacks that focus only on limiting expensive (high-cost) queries. Our method can be integrated into a range of existing black-box attacks with minimal changes. We perform both theoretical analysis and empirical evaluation on standard image classification benchmarks. Across various cost regimes, our method consistently achieves lower total query cost and smaller perturbations than existing approaches, with improvements of up to 40% in some settings.
Authors: Bastian J\"ackl, Vojt\v{e}ch Kloda, Daniel A. Keim, Jakub Loko\v{c}
Abstract: Advances in multimodal text-image models have enabled effective text-based querying in extensive image collections. While these models show convincing performance for everyday life scenes, querying in highly homogeneous, specialized domains remains challenging. The primary problem is that users can often provide only vague textual descriptions as they lack expert knowledge to discriminate between homogenous entities. This work investigates whether adding location-based prompts to complement these vague text queries can enhance retrieval performance. Specifically, we collected a dataset of 741 human annotations, each containing short and long textual descriptions and bounding boxes indicating regions of interest in challenging underwater scenes. Using these annotations, we evaluate the performance of CLIP when queried on various static sub-regions of images compared to the full image. Our results show that both a simple 3-by-3 partitioning and a 5-grid overlap significantly improve retrieval effectiveness and remain robust to perturbations of the annotation box.
Authors: Cuong Manh Hoang
Abstract: Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However, real-world datasets are always imbalanced, significantly affecting the effectiveness of these methods. To solve this problem, we propose a novel framework that performs generalized category discovery in long-tailed distributions. We first present a self-guided labeling technique that uses a learnable distribution to generate pseudo-labels, resulting in less biased classifiers. We then introduce a representation balancing process to derive discriminative representations. By mining sample neighborhoods, this process encourages the model to focus more on tail classes. We conduct experiments on public datasets to demonstrate the effectiveness of the proposed framework. The results show that our model exceeds previous state-of-the-art methods.
Authors: Arun Sharma, Mingzhou Yang, Majid Farhadloo, Subhankar Ghosh, Bharat Jayaprakash, Shashi Shekhar
Abstract: Given trajectory data, a domain-specific study area, and a user-defined threshold, we aim to find anomalous trajectories indicative of possible GPS spoofing (e.g., fake trajectory). The problem is societally important to curb illegal activities in international waters, such as unauthorized fishing and illicit oil transfers. The problem is challenging due to advances in AI generated in deep fakes generation (e.g., additive noise, fake trajectories) and lack of adequate amount of labeled samples for ground-truth verification. Recent literature shows promising results for anomalous trajectory detection using generative models despite data sparsity. However, they do not consider fine-scale spatiotemporal dependencies and prior physical knowledge, resulting in higher false-positive rates. To address these limitations, we propose a physics-informed diffusion model that integrates kinematic constraints to identify trajectories that do not adhere to physical laws. Experimental results on real-world datasets in the maritime and urban domains show that the proposed framework results in higher prediction accuracy and lower estimation error rate for anomaly detection and trajectory generation methods, respectively. Our implementation is available at https://github.com/arunshar/Physics-Informed-Diffusion-Probabilistic-Model.
URLs: https://github.com/arunshar/Physics-Informed-Diffusion-Probabilistic-Model.
Authors: Suman Mahapatra, Pradipta Maji
Abstract: Segmentation of nuclei regions from histological images enables morphometric analysis of nuclei structures, which in turn helps in the detection and diagnosis of diseases under consideration. To develop a nuclei segmentation algorithm, applicable to different types of target domain representations, image-to-image translation networks can be considered as they are invariant to target domain image representations. One of the important issues with image-to-image translation models is that they fail miserably when the information content between two image domains are asymmetric in nature. In this regard, the paper introduces a new deep generative model for segmenting nuclei structures from histological images. The proposed model considers an embedding space for handling information-disparity between information-rich histological image space and information-poor segmentation map domain. Integrating judiciously the concepts of optimal transport and measure theory, the model develops an invertible generator, which provides an efficient optimization framework with lower network complexity. The concept of invertible generator automatically eliminates the need of any explicit cycle-consistency loss. The proposed model also introduces a spatially-constrained squeeze operation within the framework of invertible generator to maintain spatial continuity within the image patches. The model provides a better trade-off between network complexity and model performance compared to other existing models having complex network architectures. The performance of the proposed deep generative model, along with a comparison with state-of-the-art nuclei segmentation methods, is demonstrated on publicly available histological image data sets.
Authors: Suman Mahapatra, Pradipta Maji
Abstract: Segmentation of nuclei regions from histological images is an important task for automated computer-aided analysis of histological images, particularly in the presence of impermissible color variation in the color appearance of stained tissue images. While color normalization enables better nuclei segmentation, accurate segmentation of nuclei structures makes color normalization rather trivial. In this respect, the paper proposes a novel deep generative model for simultaneously segmenting nuclei structures and normalizing color appearance of stained histological images.This model judiciously integrates the merits of truncated normal distribution and spatial attention. The model assumes that the latent color appearance information, corresponding to a particular histological image, is independent of respective nuclei segmentation map as well as embedding map information. The disentangled representation makes the model generalizable and adaptable as the modification or loss in color appearance information cannot be able to affect the nuclei segmentation map as well as embedding information. Also, for dealing with the stain overlap of associated histochemical reagents, the prior for latent color appearance code is assumed to be a mixture of truncated normal distributions. The proposed model incorporates the concept of spatial attention for segmentation of nuclei regions from histological images. The performance of the proposed approach, along with a comparative analysis with related state-of-the-art algorithms, has been demonstrated on publicly available standard histological image data sets.
Authors: Bhuiyan Sanjid Shafique, Ashmal Vayani, Muhammad Maaz, Hanoona Abdul Rasheed, Dinura Dissanayake, Mohammed Irfan Kurpath, Yahya Hmaiti, Go Inoue, Jean Lahoud, Md. Safirur Rashid, Shadid Intisar Quasem, Maheen Fatima, Franco Vidal, Mykola Maslych, Ketan Pravin More, Sanoojan Baliah, Hasindri Watawana, Yuhao Li, Fabian Farestam, Leon Schaller, Roman Tymtsiv, Simon Weber, Hisham Cholakkal, Ivan Laptev, Shin'ichi Satoh, Michael Felsberg, Mubarak Shah, Salman Khan, Fahad Shahbaz Khan
Abstract: Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the English language for cultural and linguistic inclusivity is yet to be investigated in the context of video LMMs. In pursuit of more inclusive video LMMs, we introduce a multilingual Video LMM benchmark, named ViMUL-Bench, to evaluate Video LMMs across 14 languages, including both low- and high-resource languages: English, Chinese, Spanish, French, German, Hindi, Arabic, Russian, Bengali, Urdu, Sinhala, Tamil, Swedish, and Japanese. Our ViMUL-Bench is designed to rigorously test video LMMs across 15 categories including eight culturally diverse categories, ranging from lifestyles and festivals to foods and rituals and from local landmarks to prominent cultural personalities. ViMUL-Bench comprises both open-ended (short and long-form) and multiple-choice questions spanning various video durations (short, medium, and long) with 8k samples that are manually verified by native language speakers. In addition, we also introduce a machine translated multilingual video training set comprising 1.2 million samples and develop a simple multilingual video LMM, named ViMUL, that is shown to provide a better tradeoff between high-and low-resource languages for video understanding. We hope our ViMUL-Bench and multilingual video LMM along with a large-scale multilingual video training set will help ease future research in developing cultural and linguistic inclusive multilingual video LMMs. Our proposed benchmark, video LMM and training data will be publicly released at https://mbzuai-oryx.github.io/ViMUL/.
Authors: LASA Team, Weiwen Xu, Hou Pong Chan, Long Li, Mahani Aljunied, Ruifeng Yuan, Jianyu Wang, Chenghao Xiao, Guizhen Chen, Chaoqun Liu, Zhaodonghui Li, Yu Sun, Junao Shen, Chaojun Wang, Jie Tan, Deli Zhao, Tingyang Xu, Hao Zhang, Yu Rong
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datasets and advanced training strategies. However, their effectiveness in medical applications remains limited due to the inherent discrepancies between data and tasks in medical scenarios and those in the general domain. Concretely, existing medical MLLMs face the following critical limitations: (1) limited coverage of medical knowledge beyond imaging, (2) heightened susceptibility to hallucinations due to suboptimal data curation processes, (3) lack of reasoning capabilities tailored for complex medical scenarios. To address these challenges, we first propose a comprehensive data curation procedure that (1) efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general-domain data; and (2) synthesizes accurate medical captions, visual question answering (VQA), and reasoning samples. As a result, we build a multimodal dataset enriched with extensive medical knowledge. Building on the curated data, we introduce our medical-specialized MLLM: Lingshu. Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities progressively. Besides, we preliminarily explore the potential of applying reinforcement learning with verifiable rewards paradigm to enhance Lingshu's medical reasoning ability. Additionally, we develop MedEvalKit, a unified evaluation framework that consolidates leading multimodal and textual medical benchmarks for standardized, fair, and efficient model assessment. We evaluate the performance of Lingshu on three fundamental medical tasks, multimodal QA, text-based QA, and medical report generation. The results show that Lingshu consistently outperforms the existing open-source multimodal models on most tasks ...
Authors: Anushka Jha, Tanushree Dewangan, Mukul Lokhande, Santosh Kumar Vishvakarma
Abstract: Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degradation. QForce-RL takes advantages from E2HRL to reduce overall RL actions to learn desired policy and QuaRL for quantization based SIMD for hardware acceleration. We have also provided detailed analysis for different RL environments, with emphasis on model size, parameters, and accelerated compute ops. The architecture is scalable for resource-constrained devices and provide parametrized efficient deployment with flexibility in latency, throughput, power, and energy efficiency. The proposed QForce-RL provides performance enhancement up to 2.3x and better FPS - 2.6x compared to SoTA works.
Authors: Zhican Wang, Guanghui He, Dantong Liu, Lingjun Gao, Shell Xu Hu, Chen Zhang, Zhuoran Song, Nicholas Lane, Wayne Luk, Hongxiang Fan
Abstract: 3D Gaussian Splatting (3DGS) has recently gained significant attention for high-quality and efficient view synthesis, making it widely adopted in fields such as AR/VR, robotics, and autonomous driving. Despite its impressive algorithmic performance, real-time rendering on resource-constrained devices remains a major challenge due to tight power and area budgets. This paper presents an architecture-algorithm co-design to address these inefficiencies. First, we reveal substantial redundancy caused by repeated computation of common terms/expressions during the conventional rasterization. To resolve this, we propose axis-oriented rasterization, which pre-computes and reuses shared terms along both the X and Y axes through a dedicated hardware design, effectively reducing multiply-and-add (MAC) operations by up to 63%. Second, by identifying the resource and performance inefficiency of the sorting process, we introduce a novel neural sorting approach that predicts order-independent blending weights using an efficient neural network, eliminating the need for costly hardware sorters. A dedicated training framework is also proposed to improve its algorithmic stability. Third, to uniformly support rasterization and neural network inference, we design an efficient reconfigurable processing array that maximizes hardware utilization and throughput. Furthermore, we introduce a $\pi$-trajectory tile schedule, inspired by Morton encoding and Hilbert curve, to optimize Gaussian reuse and reduce memory access overhead. Comprehensive experiments demonstrate that the proposed design preserves rendering quality while achieving a speedup of $23.4\sim27.8\times$ and energy savings of $28.8\sim51.4\times$ compared to edge GPUs for real-world scenes. We plan to open-source our design to foster further development in this field.
Authors: Wenrui Zhou, Shu Yang, Qingsong Yang, Zikun Guo, Lijie Hu, Di Wang
Abstract: As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistency and reliability is of critical importance. However, sycophancy, the tendency of these models to align with user input even when it contradicts the visual evidence, undermines their trustworthiness in such contexts. Current sycophancy research has largely overlooked its specific manifestations in the video-language domain, resulting in a notable absence of systematic benchmarks and targeted evaluations to understand how Video-LLMs respond under misleading user input. To fill this gap, we propose VISE (Video-LLM Sycophancy Benchmarking and Evaluation), the first dedicated benchmark designed to evaluate sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. Specifically, VISE pioneeringly brings linguistic perspectives on sycophancy into the visual domain, enabling fine-grained analysis across multiple sycophancy types and interaction patterns. In addition, we explore key-frame selection as an interpretable, training-free mitigation strategy, which reveals potential paths for reducing sycophantic bias by strengthening visual grounding.
Authors: Liangliang You, Junchi Yao, Shu Yang, Guimin Hu, Lijie Hu, Di Wang
Abstract: While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Sequence Hallucination Eradication), a lightweight, two-stage framework that (1) detects hallucinations via visual-textual alignment check using our proposed adaptive temporal window and (2) mitigates them via orthogonal projection onto the joint embedding space. We also propose a new metric (BEACH) to quantify behavioral hallucination severity. Empirical results on standard benchmarks demonstrate that SHE reduces behavioral hallucination by over 10% on BEACH while maintaining descriptive accuracy.
Authors: Lei Li, Angela Dai
Abstract: We present HOI-PAGE, a new approach to synthesizing 4D human-object interactions (HOIs) from text prompts in a zero-shot fashion, driven by part-level affordance reasoning. In contrast to prior works that focus on global, whole body-object motion for 4D HOI synthesis, we observe that generating realistic and diverse HOIs requires a finer-grained understanding -- at the level of how human body parts engage with object parts. We thus introduce Part Affordance Graphs (PAGs), a structured HOI representation distilled from large language models (LLMs) that encodes fine-grained part information along with contact relations. We then use these PAGs to guide a three-stage synthesis: first, decomposing input 3D objects into geometric parts; then, generating reference HOI videos from text prompts, from which we extract part-based motion constraints; finally, optimizing for 4D HOI motion sequences that not only mimic the reference dynamics but also satisfy part-level contact constraints. Extensive experiments show that our approach is flexible and capable of generating complex multi-object or multi-person interaction sequences, with significantly improved realism and text alignment for zero-shot 4D HOI generation.
Authors: Tong Xiao, Xin Xu, Zhenya Huang, Hongyu Gao, Quan Liu, Qi Liu, Enhong Chen
Abstract: Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies have applied Reinforcement Learning with Verifiable Rewards (RLVR) to the multimodal domain in order to enhance the reasoning abilities of MLLMs. However, these works largely overlook the enhancement of multimodal perception capabilities in MLLMs, which serve as a core prerequisite and foundational component of complex multimodal reasoning. Through McNemar's test, we find that existing RLVR method fails to effectively enhance the multimodal perception capabilities of MLLMs, thereby limiting their further improvement in multimodal reasoning. To address this limitation, we propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately, thereby can effectively incentivizing both their multimodal perception and reasoning capabilities. Specifically, we first collect textual visual annotations from the CoT trajectories of multimodal problems, which will serve as visual references for reward assignment. During RLVR training, we employ a judging LLM to assess the consistency between the visual annotations and the responses generated by MLLM, and assign the visual perception reward based on these consistency judgments. Extensive experiments on several multimodal reasoning benchmarks demonstrate the effectiveness of our Perception-R1, which achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
Authors: Shuvashis Sarker
Abstract: Brain tumors, regardless of being benign or malignant, pose considerable health risks, with malignant tumors being more perilous due to their swift and uncontrolled proliferation, resulting in malignancy. Timely identification is crucial for enhancing patient outcomes, particularly in nations such as Bangladesh, where healthcare infrastructure is constrained. Manual MRI analysis is arduous and susceptible to inaccuracies, rendering it inefficient for prompt diagnosis. This research sought to tackle these problems by creating an automated brain tumor classification system utilizing MRI data obtained from many hospitals in Bangladesh. Advanced deep learning models, including VGG16, VGG19, and ResNet50, were utilized to classify glioma, meningioma, and various brain cancers. Explainable AI (XAI) methodologies, such as Grad-CAM and Grad-CAM++, were employed to improve model interpretability by emphasizing the critical areas in MRI scans that influenced the categorization. VGG16 achieved the most accuracy, attaining 99.17%. The integration of XAI enhanced the system's transparency and stability, rendering it more appropriate for clinical application in resource-limited environments such as Bangladesh. This study highlights the capability of deep learning models, in conjunction with explainable artificial intelligence (XAI), to enhance brain tumor detection and identification in areas with restricted access to advanced medical technologies.
Authors: Shuvashis Sarker
Abstract: COVID-19 is a rapidly spreading and highly infectious virus which has triggered a global pandemic, profoundly affecting millions across the world. The pandemic has introduced unprecedented challenges in public health, economic stability, and societal structures, necessitating the implementation of extensive and multifaceted health interventions globally. It had a tremendous impact on Bangladesh by April 2024, with around 29,495 fatalities and more than 2 million confirmed cases. This study focuses on improving COVID-19 detection in CXR images by utilizing a dataset of 4,350 images from Bangladesh categorized into four classes: Normal, Lung-Opacity, COVID-19 and Viral-Pneumonia. ML, DL and TL models are employed with the VGG19 model achieving an impressive 98% accuracy. LIME is used to explain model predictions, highlighting the regions and features influencing classification decisions. SMOTE is applied to address class imbalances. By providing insight into both correct and incorrect classifications, the study emphasizes the importance of XAI in enhancing the transparency and reliability of models, ultimately improving the effectiveness of detection from CXR images.
Authors: Jiachen Zhong, Yiting Wang, Di Zhu, Ziwei Wang
Abstract: Lung cancer remains one of the most prevalent and fatal diseases worldwide, demanding accurate and timely diagnosis and treatment. Recent advancements in large AI models have significantly enhanced medical image understanding and clinical decision-making. This review systematically surveys the state-of-the-art in applying large AI models to lung cancer screening, diagnosis, prognosis, and treatment. We categorize existing models into modality-specific encoders, encoder-decoder frameworks, and joint encoder architectures, highlighting key examples such as CLIP, BLIP, Flamingo, BioViL-T, and GLoRIA. We further examine their performance in multimodal learning tasks using benchmark datasets like LIDC-IDRI, NLST, and MIMIC-CXR. Applications span pulmonary nodule detection, gene mutation prediction, multi-omics integration, and personalized treatment planning, with emerging evidence of clinical deployment and validation. Finally, we discuss current limitations in generalizability, interpretability, and regulatory compliance, proposing future directions for building scalable, explainable, and clinically integrated AI systems. Our review underscores the transformative potential of large AI models to personalize and optimize lung cancer care.
Authors: Arian Askari, Emmanouil Stergiadis, Ilya Gusev, Moran Beladev
Abstract: We present HotelMatch-LLM, a multimodal dense retrieval model for the travel domain that enables natural language property search, addressing the limitations of traditional travel search engines which require users to start with a destination and editing search parameters. HotelMatch-LLM features three key innovations: (1) Domain-specific multi-task optimization with three novel retrieval, visual, and language modeling objectives; (2) Asymmetrical dense retrieval architecture combining a small language model (SLM) for efficient online query processing and a large language model (LLM) for embedding hotel data; and (3) Extensive image processing to handle all property image galleries. Experiments on four diverse test sets show HotelMatch-LLM significantly outperforms state-of-the-art models, including VISTA and MARVEL. Specifically, on the test set -- main query type -- we achieve 0.681 for HotelMatch-LLM compared to 0.603 for the most effective baseline, MARVEL. Our analysis highlights the impact of our multi-task optimization, the generalizability of HotelMatch-LLM across LLM architectures, and its scalability for processing large image galleries.
Authors: Marco P. M. de Souza, Juciane G. Maia, Lilian N. de Andrade
Abstract: We present Pendulum Tracker, a computer vision-based application that enables real-time measurement of the oscillatory motion of a physical pendulum. Integrated into the educational platform SimuF\'isica, the system uses the OpenCV.js library and runs directly in the browser, working on computers, tablets, and smartphones. The application automatically detects the pendulum's position via the device's camera, displaying in real time the angle-versus-time graph and estimates of the oscillation period. Experimental case studies demonstrate its effectiveness in measuring the period, determining gravitational acceleration, and analyzing damped oscillations. The results show excellent agreement with theoretical predictions, confirming the system's accuracy and its applicability in educational contexts. The accessible interface and the ability to export raw data make Pendulum Tracker a versatile tool for experimental physics teaching.
Authors: Yijie Deng, Shuaihang Yuan, Congcong Wen, Hao Huang, Anthony Tzes, Geeta Chandra Raju Bethala, Yi Fang
Abstract: Spatial awareness is a critical capability for embodied agents, as it enables them to anticipate and reason about unobserved regions. The primary challenge arises from learning the distribution of indoor semantics, complicated by sparse, imbalanced object categories and diverse spatial scales. Existing methods struggle to robustly generate unobserved areas in real time and do not generalize well to new environments. To this end, we propose \textbf{MapBERT}, a novel framework designed to effectively model the distribution of unseen spaces. Motivated by the observation that the one-hot encoding of semantic maps aligns naturally with the binary structure of bit encoding, we, for the first time, leverage a lookup-free BitVAE to encode semantic maps into compact bitwise tokens. Building on this, a masked transformer is employed to infer missing regions and generate complete semantic maps from limited observations. To enhance object-centric reasoning, we propose an object-aware masking strategy that masks entire object categories concurrently and pairs them with learnable embeddings, capturing implicit relationships between object embeddings and spatial tokens. By learning these relationships, the model more effectively captures indoor semantic distributions crucial for practical robotic tasks. Experiments on Gibson benchmarks show that MapBERT achieves state-of-the-art semantic map generation, balancing computational efficiency with accurate reconstruction of unobserved regions.
Authors: Philip Liu, Sparsh Bansal, Jimmy Dinh, Aditya Pawar, Ramani Satishkumar, Shail Desai, Neeraj Gupta, Xin Wang, Shu Hu
Abstract: The integration of deep learning-based glaucoma detection with large language models (LLMs) presents an automated strategy to mitigate ophthalmologist shortages and improve clinical reporting efficiency. However, applying general LLMs to medical imaging remains challenging due to hallucinations, limited interpretability, and insufficient domain-specific medical knowledge, which can potentially reduce clinical accuracy. Although recent approaches combining imaging models with LLM reasoning have improved reporting, they typically rely on a single generalist agent, restricting their capacity to emulate the diverse and complex reasoning found in multidisciplinary medical teams. To address these limitations, we propose MedChat, a multi-agent diagnostic framework and platform that combines specialized vision models with multiple role-specific LLM agents, all coordinated by a director agent. This design enhances reliability, reduces hallucination risk, and enables interactive diagnostic reporting through an interface tailored for clinical review and educational use. Code available at https://github.com/Purdue-M2/MedChat.
Authors: Ziwen Wang, Jiajun Fan, Thao Nguyen, Heng Ji, Ge Liu
Abstract: Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1) Without explicit regulation of the embedding distribution, semantically related instances can inadvertently be pushed apart unless complementary signals guide pair selection, and (2) excessive reliance on large in-batch negatives and tailored augmentations hinders generalization. To address these limitations, we propose Variational Supervised Contrastive Learning (VarCon), which reformulates supervised contrastive learning as variational inference over latent class variables and maximizes a posterior-weighted evidence lower bound (ELBO) that replaces exhaustive pair-wise comparisons for efficient class-aware matching and grants fine-grained control over intra-class dispersion in the embedding space. Trained exclusively on image data, our experiments on CIFAR-10, CIFAR-100, ImageNet-100, and ImageNet-1K show that VarCon (1) achieves state-of-the-art performance for contrastive learning frameworks, reaching 79.36% Top-1 accuracy on ImageNet-1K and 78.29% on CIFAR-100 with a ResNet-50 encoder while converging in just 200 epochs; (2) yields substantially clearer decision boundaries and semantic organization in the embedding space, as evidenced by KNN classification, hierarchical clustering results, and transfer-learning assessments; and (3) demonstrates superior performance in few-shot learning than supervised baseline and superior robustness across various augmentation strategies.
Authors: Gaoyu Chen
Abstract: Medical image segmentation plays a crucial role in clinical medicine, serving as a tool for auxiliary diagnosis, treatment planning, and disease monitoring, thus facilitating physicians in the study and treatment of diseases. However, existing medical image segmentation methods are limited by the weak semantic expression of the target segmentation regions, which is caused by the low contrast between the target and non-target segmentation regions. To address this limitation, text prompt information has greast potential to capture the lesion location. However, existing text-guided methods suffer from insufficient cross-modal interaction and inadequate cross-modal feature expression. To resolve these issues, we propose the Text-guided Multi-stage Cross-perception network (TMC). In TMC, we introduce a multistage cross-attention module to enhance the model's understanding of semantic details and a multi-stage alignment loss to improve the consistency of cross-modal semantics. The results of the experiments demonstrate that our TMC achieves a superior performance with Dice of 84.77%, 78.50%, 88.73% in three public datasets (QaTa-COV19, MosMedData and Breast), outperforming UNet based networks and text-guided methods.
Authors: Hongyu Wang, Chuyan Xiong, Ruiping Wang, Xilin Chen
Abstract: Vision-Language-Action (VLA) models have shown impressive capabilities across a wide range of robotics manipulation tasks. However, their growing model size poses significant challenges for deployment on resource-constrained robotic systems. While 1-bit pretraining has proven effective for enhancing the inference efficiency of large language models with minimal performance loss, its application to VLA models remains underexplored. In this work, we present BitVLA, the first 1-bit VLA model for robotics manipulation, in which every parameter is ternary, i.e., {-1, 0, 1}. To further reduce the memory footprint of the vision encoder, we propose the distillation-aware training strategy that compresses the full-precision encoder to 1.58-bit weights. During this process, a full-precision encoder serves as a teacher model to better align latent representations. Despite the lack of large-scale robotics pretraining, BitVLA achieves performance comparable to the state-of-the-art model OpenVLA-OFT with 4-bit post-training quantization on the LIBERO benchmark, while consuming only 29.8% of the memory. These results highlight BitVLA's promise for deployment on memory-constrained edge devices. We release the code and model weights in https://github.com/ustcwhy/BitVLA.
Authors: Brian Gordon, Yonatan Bitton, Andreea Marzoca, Yasumasa Onoe, Xiao Wang, Daniel Cohen-Or, Idan Szpektor
Abstract: Large Vision-Language Models (VLMs) now generate highly detailed, paragraphlength image captions, yet evaluating their factual accuracy remains challenging. Current methods often miss fine-grained errors, being designed for shorter texts or lacking datasets with verified inaccuracies. We introduce DOCCI-Critique, a benchmark with 1,400 VLM-generated paragraph captions (100 images, 14 VLMs) featuring over 10,216 sentence-level human annotations of factual correctness and explanatory rationales for errors, all within paragraph context. Building on this, we develop VNLI-Critique, a model for automated sentence-level factuality classification and critique generation. We highlight three key applications: (1) VNLI-Critique demonstrates robust generalization, validated by state-of-the-art performance on the M-HalDetect benchmark and strong results in CHOCOLATE claim verification. (2) The VNLI-Critique driven AutoRater for DOCCI-Critique provides reliable VLM rankings, showing excellent alignment with human factuality judgments (e.g., 0.98 Spearman). (3) An innovative Critic-and-Revise pipeline, where critiques from VNLI-Critique guide LLM-based corrections, achieves substantial improvements in caption factuality (e.g., a 46% gain on DetailCaps-4870). Our work offers a crucial benchmark alongside practical tools, designed to significantly elevate the standards for fine-grained evaluation and foster the improvement of VLM image understanding. Project page: https://google.github.io/unblocking-detail-caption
Authors: Zeyu Xiao, Zhenyi Wu, Mingyang Sun, Qipeng Yan, Yufan Guo, Zhuoer Liang, Lihua Zhang
Abstract: 3D Gaussian Splatting has achieved remarkable success in reconstructing both static and dynamic 3D scenes. However, in a scene represented by 3D Gaussian primitives, interactions between objects suffer from inaccurate 3D segmentation, imprecise deformation among different materials, and severe rendering artifacts. To address these challenges, we introduce PIG: Physically-Based Multi-Material Interaction with 3D Gaussians, a novel approach that combines 3D object segmentation with the simulation of interacting objects in high precision. Firstly, our method facilitates fast and accurate mapping from 2D pixels to 3D Gaussians, enabling precise 3D object-level segmentation. Secondly, we assign unique physical properties to correspondingly segmented objects within the scene for multi-material coupled interactions. Finally, we have successfully embedded constraint scales into deformation gradients, specifically clamping the scaling and rotation properties of the Gaussian primitives to eliminate artifacts and achieve geometric fidelity and visual consistency. Experimental results demonstrate that our method not only outperforms the state-of-the-art (SOTA) in terms of visual quality, but also opens up new directions and pipelines for the field of physically realistic scene generation.
Authors: Xihua Sheng, Peilin Chen, Meng Wang, Li Zhang, Shiqi Wang, Dapeng Oliver Wu
Abstract: With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame codecs directly adopt P-frame coding tools without adequately addressing the unique challenges of B-frame compression, leading to suboptimal performance. To bridge this gap, we propose novel enhancements for motion compression and temporal fusion for neural B-frame coding. First, we design a fine-grained motion compression method. This method incorporates an interactive dual-branch motion auto-encoder with per-branch adaptive quantization steps, which enables fine-grained compression of bi-directional motion vectors while accommodating their asymmetric bitrate allocation and reconstruction quality requirements. Furthermore, this method involves an interactive motion entropy model that exploits correlations between bi-directional motion latent representations by interactively leveraging partitioned latent segments as directional priors. Second, we propose a selective temporal fusion method that predicts bi-directional fusion weights to achieve discriminative utilization of bi-directional multi-scale temporal contexts with varying qualities. Additionally, this method introduces a hyperprior-based implicit alignment mechanism for contextual entropy modeling. By treating the hyperprior as a surrogate for the contextual latent representation, this mechanism implicitly mitigates the misalignment in the fused bi-directional temporal priors. Extensive experiments demonstrate that our proposed codec outperforms state-of-the-art neural B-frame codecs and achieves comparable or even superior compression performance to the H.266/VVC reference software under random-access configurations.
Authors: Haizhao Jing, Haokui Zhang, Zhenhao Shang, Rong Xiao, Peng Wang, Yanning Zhang
Abstract: Neural Architecture Representation Learning aims to transform network models into feature representations for predicting network attributes, playing a crucial role in deploying and designing networks for real-world applications. Recently, inspired by the success of transformers, transformer-based models integrated with Graph Neural Networks (GNNs) have achieved significant progress in representation learning. However, current methods still have some limitations. First, existing methods overlook hardware attribute information, which conflicts with the current trend of diversified deep learning hardware and limits the practical applicability of models. Second, current encoding approaches rely on static adjacency matrices to represent topological structures, failing to capture the structural differences between computational nodes, which ultimately compromises encoding effectiveness. In this paper, we introduce LeDG-Former, an innovative framework that addresses these limitations through the synergistic integration of language-based semantic embedding and dynamic graph representation learning. Specifically, inspired by large language models (LLMs), we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space through tokenization and LLM processing, enabling zero-shot prediction across different hardware platforms for the first time. Then, we propose a dynamic graph-based transformer for modeling neural architectures, resulting in improved neural architecture modeling performance. On the NNLQP benchmark, LeDG-Former surpasses previous methods, establishing a new SOTA while demonstrating the first successful cross-hardware latency prediction capability. Furthermore, our framework achieves superior performance on the cell-structured NAS-Bench-101 and NAS-Bench-201 datasets.
Authors: Avinash Kori, Francesca Toni, Ben Glocker
Abstract: Modular object-centric representations are essential for *human-like reasoning* but are challenging to obtain under spatial ambiguities, *e.g. due to occlusions and view ambiguities*. However, addressing challenges presents both theoretical and practical difficulties. We introduce a novel multi-view probabilistic approach that aggregates view-specific slots to capture *invariant content* information while simultaneously learning disentangled global *viewpoint-level* information. Unlike prior single-view methods, our approach resolves spatial ambiguities, provides theoretical guarantees for identifiability, and requires *no viewpoint annotations*. Extensive experiments on standard benchmarks and novel complex datasets validate our method's robustness and scalability.
Authors: Rajat Rasal, Avinash Kori, Fabio De Sousa Ribeiro, Tian Xia, Ben Glocker
Abstract: Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic latent spaces which can be manipulated for causal control, they struggle with scalability and fidelity. Advancements in diffusion models present opportunities for improving counterfactual image editing, having demonstrated state-of-the-art visual quality, human-aligned perception and representation learning capabilities. Here, we present a suite of diffusion-based causal mechanisms, introducing the notions of spatial, semantic and dynamic abduction. We propose a general framework that integrates semantic representations into diffusion models through the lens of Pearlian causality to edit images via a counterfactual reasoning process. To our knowledge, this is the first work to consider high-level semantic identity preservation for diffusion counterfactuals and to demonstrate how semantic control enables principled trade-offs between faithful causal control and identity preservation.
Authors: Shuja Khalid, Mohamed Ibrahim, Yang Liu
Abstract: We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing reconstructions that cannot extrapolate finer details than are present in the training views. Our work breaks this limitation through a lightweight generative model that predicts and refines additional 3D Gaussians where needed most. The key innovation is our Hessian-assisted sampling strategy, which intelligently identifies regions that are likely to benefit from densification, ensuring computational efficiency. Unlike computationally intensive GANs or diffusion approaches, our method operates in real-time (0.015s per inference on a single consumer-grade GPU), making it practical for interactive applications. Comprehensive experiments demonstrate significant improvements in both geometric accuracy and rendering quality compared to state-of-the-art methods, establishing a new paradigm for resolution-free 3D scene enhancement.
Authors: Kevin Rojas, Yuchen Zhu, Sichen Zhu, Felix X. -F. Ye, Molei Tao
Abstract: Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation. On the contrary, the joint generation of multimodal data through diffusion models is still in the early stages of exploration. Existing approaches heavily rely on external preprocessing protocols, such as tokenizers and variational autoencoders, to harmonize varied data representations into a unified, unimodal format. This process heavily demands the high accuracy of encoders and decoders, which can be problematic for applications with limited data. To lift this restriction, we propose a novel framework for building multimodal diffusion models on arbitrary state spaces, enabling native generation of coupled data across different modalities. By introducing an innovative decoupled noise schedule for each modality, we enable both unconditional and modality-conditioned generation within a single model simultaneously. We empirically validate our approach for text-image generation and mixed-type tabular data synthesis, demonstrating that it achieves competitive performance.
Authors: Allen Tu, Haiyang Ying, Alex Hanson, Yonghan Lee, Tom Goldstein, Matthias Zwicker
Abstract: Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian. However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements. In this paper, we present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques. First, we propose a temporal sensitivity pruning score that identifies and removes Gaussians with low contribution to the dynamic scene reconstruction. We also introduce an annealing smooth pruning mechanism that improves pruning robustness in real-world scenes with imprecise camera poses. Second, we propose GroupFlow, a motion analysis technique that clusters Gaussians by trajectory similarity and predicts a single rigid transformation per group instead of separate deformations for each Gaussian. Together, our techniques accelerate rendering by $10.37\times$, reduce model size by $7.71\times$, and shorten training time by $2.71\times$ on the NeRF-DS dataset. SpeeDe3DGS also improves rendering speed by $4.20\times$ and $58.23\times$ on the D-NeRF and HyperNeRF vrig datasets. Our methods are modular and can be integrated into any deformable 3DGS or 4DGS framework.
Authors: Rishit Dagli, Yushi Guan, Sankeerth Durvasula, Mohammadreza Mofayezi, Nandita Vijaykumar
Abstract: We propose Squeeze3D, a novel framework that leverages implicit prior knowledge learnt by existing pre-trained 3D generative models to compress 3D data at extremely high compression ratios. Our approach bridges the latent spaces between a pre-trained encoder and a pre-trained generation model through trainable mapping networks. Any 3D model represented as a mesh, point cloud, or a radiance field is first encoded by the pre-trained encoder and then transformed (i.e. compressed) into a highly compact latent code. This latent code can effectively be used as an extremely compressed representation of the mesh or point cloud. A mapping network transforms the compressed latent code into the latent space of a powerful generative model, which is then conditioned to recreate the original 3D model (i.e. decompression). Squeeze3D is trained entirely on generated synthetic data and does not require any 3D datasets. The Squeeze3D architecture can be flexibly used with existing pre-trained 3D encoders and existing generative models. It can flexibly support different formats, including meshes, point clouds, and radiance fields. Our experiments demonstrate that Squeeze3D achieves compression ratios of up to 2187x for textured meshes, 55x for point clouds, and 619x for radiance fields while maintaining visual quality comparable to many existing methods. Squeeze3D only incurs a small compression and decompression latency since it does not involve training object-specific networks to compress an object.
Authors: Jixiang Hong, Yiran Zhang, Guanzhong Wang, Yi Liu, Ji-Rong Wen, Rui Yan
Abstract: Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate image-text alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are inverse dual tasks, we introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs. Specifically, we sample multiple outputs for a given input in one task domain, then reverse the input-output pairs to compute the dual likelihood of the model as self-rewards for optimization. Extensive experimental results on visual understanding and generation benchmarks demonstrate that our method can effectively enhance the performance of the model without any external supervision, especially achieving remarkable improvements in text-to-image tasks.
Authors: Boya Zeng, Yida Yin, Zhiqiu Xu, Zhuang Liu
Abstract: Generative models, with their success in image and video generation, have recently been explored for synthesizing effective neural network weights. These approaches take trained neural network checkpoints as training data, and aim to generate high-performing neural network weights during inference. In this work, we examine four representative methods on their ability to generate novel model weights, i.e., weights that are different from the checkpoints seen during training. Surprisingly, we find that these methods synthesize weights largely by memorization: they produce either replicas, or at best simple interpolations, of the training checkpoints. Current methods fail to outperform simple baselines, such as adding noise to the weights or taking a simple weight ensemble, in obtaining different and simultaneously high-performing models. We further show that this memorization cannot be effectively mitigated by modifying modeling factors commonly associated with memorization in image diffusion models, or applying data augmentations. Our findings provide a realistic assessment of what types of data current generative models can model, and highlight the need for more careful evaluation of generative models in new domains. Our code is available at https://github.com/boyazeng/weight_memorization.
Authors: Penghao Wu, Shengnan Ma, Bo Wang, Jiaheng Yu, Lewei Lu, Ziwei Liu
Abstract: Multimodal Large Language Models (MLLMs) have shown great potential in revolutionizing Graphical User Interface (GUI) automation. However, existing GUI models mostly rely on learning from nearly error-free offline trajectories, thus lacking reflection and error recovery capabilities. To bridge this gap, we propose GUI-Reflection, a novel framework that explicitly integrates self-reflection and error correction capabilities into end-to-end multimodal GUI models throughout dedicated training stages: GUI-specific pre-training, offline supervised fine-tuning (SFT), and online reflection tuning. GUI-reflection enables self-reflection behavior emergence with fully automated data generation and learning processes without requiring any human annotation. Specifically, 1) we first propose scalable data pipelines to automatically construct reflection and error correction data from existing successful trajectories. While existing GUI models mainly focus on grounding and UI understanding ability, we propose the GUI-Reflection Task Suite to learn and evaluate reflection-oriented abilities explicitly. 2) Furthermore, we built a diverse and efficient environment for online training and data collection of GUI models on mobile devices. 3) We also present an iterative online reflection tuning algorithm leveraging the proposed environment, enabling the model to continuously enhance its reflection and error correction abilities. Our framework equips GUI agents with self-reflection and correction capabilities, paving the way for more robust, adaptable, and intelligent GUI automation, with all data, models, environments, and tools to be released publicly.
Authors: Nasser Aghazadeh, Ladan Sharafyan Cigaroudy
Abstract: The main contribution of this paper is to propose an iterative procedure for tubular structure segmentation of 2D images, which combines tight frame of Curvelet transforms with a SURE technique thresholding which is based on principle obtained by minimizing Stein Unbiased Risk Estimate for denoising. This proposed algorithm is mainly based on the TFA proposal presented in [1, 9], which we use eigenvectors of Hessian matrix of image for improving this iterative part in segmenting unclear and narrow vessels and filling the gap between separate pieces of detected vessels. The experimental results are presented to demonstrate the effectiveness of the proposed model.
Authors: Khalil Mathieu Hannouch, Stephan Chalup
Abstract: The topological analysis of four-dimensional (4D) image-type data is challenged by the immense size that these datasets can reach. This can render the direct application of methods, like persistent homology and convolutional neural networks (CNNs), impractical due to computational constraints. This study aims to estimate the topology type of 4D image-type data cubes that exhibit topological intricateness and size above our current processing capacity. The experiments using synthesised 4D data and a real-world 3D data set demonstrate that it is possible to circumvent computational complexity issues by applying downscaling methods to the data before training a CNN. This is achievable even when persistent homology software indicates that downscaling can significantly alter the homology of the training data. When provided with downscaled test data, the CNN can still estimate the Betti numbers of the original sample cubes with over 80\% accuracy, which outperforms the persistent homology approach, whose accuracy deteriorates under the same conditions. The accuracy of the CNNs can be further increased by moving from a mathematically-guided approach to a more vision-based approach where cavity types replace the Betti numbers as training targets.
Authors: Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu
Abstract: Deep learning (DL) has advanced the field of dense prediction, while gradually dissolving the inherent barriers between different tasks. However, most existing works focus on designing architectures and constructing visual cues only for the specific task, which ignores the potential uniformity introduced by the DL paradigm. In this paper, we attempt to construct a novel $\underline{ComP}$lementary $\underline{tr}$ansformer, $\textbf{ComPtr}$, for diverse bi-source dense prediction tasks. Specifically, unlike existing methods that over-specialize in a single task or a subset of tasks, ComPtr starts from the more general concept of bi-source dense prediction. Based on the basic dependence on information complementarity, we propose consistency enhancement and difference awareness components with which ComPtr can evacuate and collect important visual semantic cues from different image sources for diverse tasks, respectively. ComPtr treats different inputs equally and builds an efficient dense interaction model in the form of sequence-to-sequence on top of the transformer. This task-generic design provides a smooth foundation for constructing the unified model that can simultaneously deal with various bi-source information. In extensive experiments across several representative vision tasks, i.e. remote sensing change detection, RGB-T crowd counting, RGB-D/T salient object detection, and RGB-D semantic segmentation, the proposed method consistently obtains favorable performance. The code will be available at https://github.com/lartpang/ComPtr.
Authors: Rongsheng Wang, Qingsong Yao, Zihang Jiang, Haoran Lai, Zhiyang He, Xiaodong Tao, S. Kevin Zhou
Abstract: Despite significant advancements in medical vision-language pre-training, existing methods have largely overlooked the inherent linguistic complexity and imbalanced isssue within medical reports, as well as the complex cross-modality contextual relationships between texts and images. To close this gap, we propose a novel Entity-centered Context-aware Medical Vision-language Pre-training (ECAMP) framework, which establishes a more entity-centered, context-sensitive, and balanced understanding of medical reports to effectively pre-train the vision encoder. We first distill entity-centered context from medical reports utilizing large language models, enabling ECAMP to draw more precise supervision from the text modality. By further incorporating entity-aware re-balanced factor and descriptor masking strategies into masked languange modeling, ECAMP significantly enhances the knowledge of entities within the reports. A context-guided super-resolution task is proposed alongside a multi-scale context fusion design to improve the semantic integration of both coarse and fine-level image representations, which prompts better performance for multi-scale downstream applications. ECAMP integrates these innovations together, leading to significant performance leaps over current state-of-the-art methods and establish a new standard for cross-modality pre-training in medical imaging. The effectiveness of ECAMP is demonstrated by extensive experiments on various domains and organs, which achieves cutting-edge results on multiple tasks including classification, segmentation, and detection across 5 public chest X-ray and 4 fundoscopy datasets respectively.
Authors: Long Zhao, Nitesh B. Gundavarapu, Liangzhe Yuan, Hao Zhou, Shen Yan, Jennifer J. Sun, Luke Friedman, Rui Qian, Tobias Weyand, Yue Zhao, Rachel Hornung, Florian Schroff, Ming-Hsuan Yang, David A. Ross, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Ting Liu, Boqing Gong
Abstract: We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text (e.g., ASR transcripts). The pretraining approach improves upon masked autoencoding by global-local distillation of semantic video embeddings and a token shuffling scheme, enabling VideoPrism to focus primarily on the video modality while leveraging the invaluable text associated with videos. We extensively test VideoPrism on four broad groups of video understanding tasks, from web video question answering to CV for science, achieving state-of-the-art performance on 31 out of 33 video understanding benchmarks. Our models are released at https://github.com/google-deepmind/videoprism.
Authors: Federico Nocentini, Claudio Ferrari, Stefano Berretti
Abstract: The domain of 3D talking head generation has witnessed significant progress in recent years. A notable challenge in this field consists in blending speech-related motions with expression dynamics, which is primarily caused by the lack of comprehensive 3D datasets that combine diversity in spoken sentences with a variety of facial expressions. Whereas literature works attempted to exploit 2D video data and parametric 3D models as a workaround, these still show limitations when jointly modeling the two motions. In this work, we address this problem from a different perspective, and propose an innovative data-driven technique that we used for creating a synthetic dataset, called EmoVOCA, obtained by combining a collection of inexpressive 3D talking heads and a set of 3D expressive sequences. To demonstrate the advantages of this approach, and the quality of the dataset, we then designed and trained an emotional 3D talking head generator that accepts a 3D face, an audio file, an emotion label, and an intensity value as inputs, and learns to animate the audio-synchronized lip movements with expressive traits of the face. Comprehensive experiments, both quantitative and qualitative, using our data and generator evidence superior ability in synthesizing convincing animations, when compared with the best performing methods in the literature. Our code and pre-trained model will be made available.
Authors: Mohammadhossein Bahari, Saeed Saadatnejad, Amirhossein Askari Farsangi, Seyed-Mohsen Moosavi-Dezfooli, Alexandre Alahi
Abstract: Predicting human trajectories is essential for the safe operation of autonomous vehicles, yet current data-driven models often lack robustness in case of noisy inputs such as adversarial examples or imperfect observations. Although some trajectory prediction methods have been developed to provide empirical robustness, these methods are heuristic and do not offer guaranteed robustness. In this work, we propose a certification approach tailored for trajectory prediction that provides guaranteed robustness. To this end, we address the unique challenges associated with trajectory prediction, such as unbounded outputs and multi-modality. To mitigate the inherent performance drop through certification, we propose a diffusion-based trajectory denoiser and integrate it into our method. Moreover, we introduce new certified performance metrics to reliably measure the trajectory prediction performance. Through comprehensive experiments, we demonstrate the accuracy and robustness of the certified predictors and highlight their advantages over the non-certified ones. The code is available online: https://s-attack.github.io/.
Authors: Junhyeong Cho, Kim Youwang, Hunmin Yang, Tae-Hyun Oh
Abstract: Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significantly compromised in real-world conditions, due to imperfect object segmentation by off-the-shelf models and the prevalence of occlusions. To effectively address these issues, we propose a unified regression model that integrates segmentation and reconstruction, specifically designed for occlusion-aware 3D shape reconstruction. To facilitate its reconstruction in the wild, we also introduce a scalable data synthesis pipeline that simulates a wide range of variations in objects, occluders, and backgrounds. Training on our synthetic data enables the proposed model to achieve state-of-the-art zero-shot results on real-world images, using significantly fewer parameters than competing approaches.
Authors: Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Qing Yu, Go Irie, Yixuan Li, Hai Li, Ziwei Liu, Kiyoharu Aizawa
Abstract: This paper introduces a novel task to evaluate the robust understanding capability of Large Multimodal Models (LMMs), termed $\textbf{Unsolvable Problem Detection (UPD)}$. Multiple-choice question answering (MCQA) is widely used to assess the understanding capability of LMMs, but it does not guarantee that LMMs truly comprehend the answer. UPD assesses the LMM's ability to withhold answers when encountering unsolvable problems of MCQA, verifying whether the model truly understands the answer. UPD encompasses three problems: Absent Answer Detection (AAD), Incompatible Answer Set Detection (IASD), and Incompatible Visual Question Detection (IVQD), covering unsolvable cases like answer-lacking or incompatible choices and image-question mismatches. For the evaluation, we introduce the MM-UPD Bench, a benchmark for assessing performance across various ability dimensions. Our experiments reveal that even most LMMs, which demonstrate adequate performance on existing benchmarks, struggle significantly with MM-UPD, underscoring a novel aspect of trustworthiness that current benchmarks have overlooked. A detailed analysis shows that LMMs have different bottlenecks and chain-of-thought and self-reflection improved performance for LMMs with the bottleneck in their LLM capability. We hope our insights will enhance the broader understanding and development of more reliable LMMs. The code is available at https://github.com/AtsuMiyai/UPD.
Authors: Hanjing Zhou, Mingze Yin, Danny Chen, Jian Wu, JinTai Chen
Abstract: One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class. This task is challenging because target objects in the support and query images can be largely different in appearance and pose (i.e., intra-class variation). Prior works suggested that incorporating more annotated support images in few-shot settings boosts performances but increases costs due to additional manual labeling. In this paper, we propose a novel and effective approach for ONE-shot semantic segmentation, called Group-On, which packs multiple query images in batches for the benefit of mutual knowledge support within the same category. Specifically, after coarse segmentation masks of the batch of queries are predicted, query-mask pairs act as pseudo support data to enhance mask predictions mutually. To effectively steer such process, we construct an innovative MoME module, where a flexible number of mask experts are guided by a scene-driven router and work together to make comprehensive decisions, fully promoting mutual benefits of queries. Comprehensive experiments on three standard benchmarks show that, in the ONE-shot setting, Group-On significantly outperforms previous works by considerable margins. With only one annotated support image, Group-On can be even competitive with the counterparts using 5 annotated images.
Authors: Jinming Cao, Sicheng Shen, Qiu Zhou, Yifang Yin, Yangyan Li, Roger Zimmermann
Abstract: Photographing optoelectronic displays often introduces unwanted moir\'e patterns due to analog signal interference between the pixel grids of the display and the camera sensor arrays. This work identifies two problems that are largely ignored by existing image demoir\'eing approaches: 1) moir\'e patterns vary across different channels (RGB); 2) repetitive patterns are constantly observed. However, employing conventional convolutional (CNN) layers cannot address these problems. Instead, this paper presents the use of our recently proposed \emph{Shape} concept. It was originally employed to model consistent features from fragmented regions, particularly when identical or similar objects coexist in an RGB-D image. Interestingly, we find that the Shape information effectively captures the moir\'e patterns in artifact images. Motivated by this discovery, we propose a new method, ShapeMoir\'e, for image demoir\'eing. Beyond modeling shape features at the patch-level, we further extend this to the global image-level and design a novel Shape-Architecture. Consequently, our proposed method, equipped with both ShapeConv and Shape-Architecture, can be seamlessly integrated into existing approaches without introducing any additional parameters or computation overhead during inference. We conduct extensive experiments on four widely used datasets, and the results demonstrate that our ShapeMoir\'e achieves state-of-the-art performance, particularly in terms of the PSNR metric.
Authors: David Geissb\"uhler, Hatef Otroshi Shahreza, S\'ebastien Marcel
Abstract: Face recognition models are trained on large-scale datasets, which have privacy and ethical concerns. Lately, the use of synthetic data to complement or replace genuine data for the training of face recognition models has been proposed. While promising results have been obtained, it still remains unclear if generative models can yield diverse enough data for such tasks. In this work, we introduce a new method, inspired by the physical motion of soft particles subjected to stochastic Brownian forces, allowing us to sample identities distributions in a latent space under various constraints. We introduce three complementary algorithms, called Langevin, Dispersion, and DisCo, aimed at generating large synthetic face datasets. With this in hands, we generate several face datasets and benchmark them by training face recognition models, showing that data generated with our method exceeds the performance of previously GAN-based datasets and achieves competitive performance with state-of-the-art diffusion-based synthetic datasets. While diffusion models are shown to memorize training data, we prevent leakage in our new synthetic datasets, paving the way for more responsible synthetic datasets.
Authors: Alan Q. Wang, Rachit Saluja, Heejong Kim, Xinzi He, Adrian Dalca, Mert R. Sabuncu
Abstract: We present a keypoint-based foundation model for general purpose brain MRI registration, based on the recently-proposed KeyMorph framework. Our model, called BrainMorph, serves as a tool that supports multi-modal, pairwise, and scalable groupwise registration. BrainMorph is trained on a massive dataset of over 100,000 3D volumes, skull-stripped and non-skull-stripped, from nearly 16,000 unique healthy and diseased subjects. BrainMorph is robust to large misalignments, interpretable via interrogating automatically-extracted keypoints, and enables rapid and controllable generation of many plausible transformations with different alignment types and different degrees of nonlinearity at test-time. We demonstrate the superiority of BrainMorph in solving 3D rigid, affine, and nonlinear registration on a variety of multi-modal brain MRI scans of healthy and diseased subjects, in both the pairwise and groupwise setting. In particular, we show registration accuracy and speeds that surpass many classical and learning-based methods, especially in the context of large initial misalignments and large group settings. All code and models are available at https://github.com/alanqrwang/brainmorph.
Authors: Yujie Wang, Praneeth Chakravarthula, Baoquan Chen
Abstract: 3D Gaussian Splatting (3DGS) techniques have recently enabled high-quality 3D scene reconstruction and real-time novel view synthesis. These approaches, however, are limited by the pinhole camera model and lack effective modeling of defocus effects. Departing from this, we introduce DOF-GS--a new 3DGS-based framework with a finite-aperture camera model and explicit, differentiable defocus rendering, enabling it to function as a post-capture control tool. By training with multi-view images with moderate defocus blur, DOF-GS learns inherent camera characteristics and reconstructs sharp details of the underlying scene, particularly, enabling rendering of varying DOF effects through on-demand aperture and focal distance control, post-capture and optimization. Additionally, our framework extracts circle-of-confusion cues during optimization to identify in-focus regions in input views, enhancing the reconstructed 3D scene details. Experimental results demonstrate that DOF-GS supports post-capture refocusing, adjustable defocus and high-quality all-in-focus rendering, from multi-view images with uncalibrated defocus blur.
Authors: Jiahao Shao, Yuanbo Yang, Hongyu Zhou, Youmin Zhang, Yujun Shen, Vitor Guizilini, Yue Wang, Matteo Poggi, Yiyi Liao
Abstract: This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels for each frame within a clip during training while using a sliding window strategy and initializing overlapping frames with previously predicted frames without adding noise. Moreover, we design an effective training strategy to provide context within a clip. Extensive experimental results validate our design choices and demonstrate the superiority of our approach, dubbed ChronoDepth. Project page: https://xdimlab.github.io/ChronoDepth/.
Authors: Ruiyuan Lyu, Jingli Lin, Tai Wang, Shuai Yang, Xiaohan Mao, Yilun Chen, Runsen Xu, Haifeng Huang, Chenming Zhu, Dahua Lin, Jiangmiao Pang
Abstract: With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a single target to inter-target relationships, covering holistic aspects of spatial and attribute understanding. The overall pipeline incorporates powerful VLMs via carefully designed prompts to initialize the annotations efficiently and further involve humans' correction in the loop to ensure the annotations are natural, correct, and comprehensive. Built upon existing 3D scanning data, the resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks. We evaluate representative baselines on our benchmarks, analyze their capabilities in different aspects, and showcase the key problems to be addressed in the future. Furthermore, we use this high-quality dataset to train state-of-the-art 3D visual grounding and LLMs and obtain remarkable performance improvement both on existing benchmarks and in-the-wild evaluation. Codes, datasets, and benchmarks will be available at https://github.com/OpenRobotLab/EmbodiedScan.
Authors: Sebastian Hafner, Heng Fang, Hossein Azizpour, Yifang Ban
Abstract: Urbanization advances at unprecedented rates, leading to negative environmental and societal impacts. Remote sensing can help mitigate these effects by supporting sustainable development strategies with accurate information on urban growth. Deep learning-based methods have achieved promising urban change detection results from optical satellite image pairs using convolutional neural networks (ConvNets), transformers, and a multi-task learning setup. However, bi-temporal methods are limited for continuous urban change detection, i.e., the detection of changes in consecutive image pairs of satellite image time series (SITS), as they fail to fully exploit multi-temporal data (> 2 images). Existing multi-temporal change detection methods, on the other hand, collapse the temporal dimension, restricting their ability to capture continuous urban changes. Additionally, multi-task learning methods lack integration approaches that combine change and segmentation outputs. To address these challenges, we propose a continuous urban change detection framework incorporating two key modules. The temporal feature refinement (TFR) module employs self-attention to improve ConvNet-based multi-temporal building representations. The temporal dimension is preserved in the TFR module, enabling the detection of continuous changes. The multi-task integration (MTI) module utilizes Markov networks to find an optimal building map time series based on segmentation and dense change outputs. The proposed framework effectively identifies urban changes based on high-resolution SITS acquired by the PlanetScope constellation (F1 score 0.551), Gaofen-2 (F1 score 0.440), and WorldView-2 (F1 score 0.543). Moreover, our experiments on three challenging datasets demonstrate the effectiveness of the proposed framework compared to bi-temporal and multi-temporal urban change detection and segmentation methods.
Authors: Fangyuan Mao, Jilin Mei, Shun Lu, Fuyang Liu, Liang Chen, Fangzhou Zhao, Yu Hu
Abstract: Infrared imaging technology has gained significant attention for its reliable sensing ability in low visibility conditions, prompting many studies to convert the abundant RGB images to infrared images. However, most existing image translation methods treat infrared images as a stylistic variation, neglecting the underlying physical laws, which limits their practical application. To address these issues, we propose a Physics-Informed Diffusion (PID) model for translating RGB images to infrared images that adhere to physical laws. Our method leverages the iterative optimization of the diffusion model and incorporates strong physical constraints based on prior knowledge of infrared laws during training. This approach enhances the similarity between translated infrared images and the real infrared domain without increasing extra training parameters. Experimental results demonstrate that PID significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/fangyuanmao/PID.
Authors: Mariya Hendriksen, Shuo Zhang, Ridho Reinanda, Mohamed Yahya, Edgar Meij, Maarten de Rijke
Abstract: Image-Text Retrieval (ITR) systems are central to multimodal information access, with Vision-Language Models (VLMs) showing strong performance on standard benchmarks. However, these benchmarks predominantly rely on coarse-grained annotations, limiting their ability to reveal how models perform under real-world conditions, where query granularity varies. Motivated by this gap, we examine how dataset granularity and query perturbations affect retrieval performance and robustness across four architecturally diverse VLMs (ALIGN, AltCLIP, CLIP, and GroupViT). Using both standard benchmarks (MS-COCO, Flickr30k) and their fine-grained variants, we show that richer captions consistently enhance retrieval, especially in text-to-image tasks, where we observe an average improvement of 16.23%, compared to 6.44% in image-to-text. To assess robustness, we introduce a taxonomy of perturbations and conduct extensive experiments, revealing that while perturbations typically degrade performance, they can also unexpectedly improve retrieval, exposing nuanced model behaviors. Notably, word order emerges as a critical factor -- contradicting prior assumptions of model insensitivity to it. Our results highlight variation in model robustness and a dataset-dependent relationship between caption granularity and perturbation sensitivity and emphasize the necessity of evaluating models on datasets of varying granularity.
Authors: Abhi Kamboj, Anh Duy Nguyen, Minh N. Do
Abstract: In order to unlock the potential of diverse sensors, we investigate a method to transfer knowledge between time-series modalities using a multimodal \textit{temporal} representation space for Human Activity Recognition (HAR). Specifically, we explore the setting where the modality used in testing has no labeled data during training, which we refer to as Unsupervised Modality Adaptation (UMA). We categorize existing UMA approaches as Student-Teacher or Contrastive Alignment methods. These methods typically compress continuous-time data samples into single latent vectors during alignment, inhibiting their ability to transfer temporal information through real-world temporal distortions. To address this, we introduce Cross-modal Transfer Through Time (C3T), which preserves temporal information during alignment to handle dynamic sensor data better. C3T achieves this by aligning a set of temporal latent vectors across sensing modalities. Our extensive experiments on various camera+IMU datasets demonstrate that C3T outperforms existing methods in UMA by at least 8% in accuracy and shows superior robustness to temporal distortions such as time-shift, misalignment, and dilation. Our findings suggest that C3T has significant potential for developing generalizable models for time-series sensor data, opening new avenues for various multimodal applications.
Authors: Youngseok Yoon, Dainong Hu, Iain Weissburg, Yao Qin, Haewon Jeong
Abstract: Model collapse, the severe degradation of generative models when iteratively trained on their own outputs, has gained significant attention in recent years. This paper examines Chain of Diffusion, where a pretrained text-to-image diffusion model is finetuned on its own generated images. We demonstrate that severe image quality degradation was universal and identify CFG scale as the key factor impacting this model collapse. Drawing on an analogy between the Chain of Diffusion and biological evolution, we then introduce a novel theoretical analysis based on quantitative trait modeling from statistical genetics. Our theoretical analysis aligns with empirical observations of the generated images in the Chain of Diffusion. Finally, we propose Reusable Diffusion Finetuning (ReDiFine), a simple yet effective strategy inspired by genetic mutations. It operates robustly across various scenarios without requiring any hyperparameter tuning, making it a plug-and-play solution for reusable image generation.
Authors: Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Abstract: Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets, which contain multiple objects of complex textures and shapes in natural everyday scenes. To address this, we introduce Guided Latent Slot Diffusion (GLASS), a novel slot-attention model that learns in the space of generated images and uses semantic and instance guidance modules to learn better slot embeddings for various downstream tasks. Our experiments show that GLASS surpasses state-of-the-art slot-attention methods by a wide margin on tasks such as (zero-shot) object discovery and conditional image generation for real-world scenes. Moreover, GLASS enables the first application of slot attention to the compositional generation of complex, realistic scenes.
Authors: Lu Yu, Zhe Tao, Dipam Goswami, Hantao Yao, Bart{\l}omiej Twardowski, Joost Van de Weijer, Changsheng Xu
Abstract: Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously learned knowledge. Existing methods mainly rely on visual features, often neglecting the rich semantic information encoded in text. The semantic knowledge available in the label information of the images, offers important semantic information that can be related with previously acquired knowledge of semantic classes. Consequently, effectively leveraging this information throughout continual learning is expected to be beneficial. To address this, we propose integrating semantic guidance within and across tasks by capturing semantic similarity using text embeddings. We start from a pre-trained CLIP model, employ the \emph{Semantically-guided Representation Learning (SG-RL)} module for a soft-assignment towards all current task classes, and use the Semantically-guided Knowledge Distillation (SG-KD) module for enhanced knowledge transfer. Experimental results demonstrate the superiority of our method on general and fine-grained datasets. Our code can be found in https://github.com/aprilsveryown/semantically-guided-continual-learning.
URLs: https://github.com/aprilsveryown/semantically-guided-continual-learning.
Authors: Sean J. Liu, Nupur Kumari, Ariel Shamir, Jun-Yan Zhu
Abstract: Text-to-image models are powerful tools for image creation. However, the generation process is akin to a dice roll and makes it difficult to achieve a single image that captures everything a user wants. In this paper, we propose a framework for creating the desired image by compositing it from various parts of generated images, in essence forming a Generative Photomontage. Given a stack of images generated by ControlNet using the same input condition and different seeds, we let users select desired parts from the generated results using a brush stroke interface. We introduce a novel technique that takes in the user's brush strokes, segments the generated images using a graph-based optimization in diffusion feature space, and then composites the segmented regions via a new feature-space blending method. Our method faithfully preserves the user-selected regions while compositing them harmoniously. We demonstrate that our flexible framework can be used for many applications, including generating new appearance combinations, fixing incorrect shapes and artifacts, and improving prompt alignment. We show compelling results for each application and demonstrate that our method outperforms existing image blending methods and various baselines.
Authors: Shaobo Wang, Yantai Yang, Qilong Wang, Kaixin Li, Linfeng Zhang, Junchi Yan
Abstract: Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we take an initial step towards understanding various matching-based DD methods from the perspective of sample difficulty. We begin by empirically examining sample difficulty, measured by gradient norm, and observe that different matching-based methods roughly correspond to specific difficulty tendencies. We then extend the neural scaling laws of data pruning to DD to theoretically explain these matching-based methods. Our findings suggest that prioritizing the synthesis of easier samples from the original dataset can enhance the quality of distilled datasets, especially in low IPC (image-per-class) settings. Based on our empirical observations and theoretical analysis, we introduce the Sample Difficulty Correction (SDC) approach, designed to predominantly generate easier samples to achieve higher dataset quality. Our SDC can be seamlessly integrated into existing methods as a plugin with minimal code adjustments. Experimental results demonstrate that adding SDC generates higher-quality distilled datasets across 7 distillation methods and 6 datasets.
Authors: Yihao Zhang, Harpreet S. Sawhney, John J. Leonard
Abstract: Category-level object pose and shape estimation from a single depth image has recently drawn research attention due to its potential utility for tasks such as robotics manipulation. The task is particularly challenging because the three unknowns, object pose, object shape, and model-to-measurement correspondences, are compounded together, but only a single view of depth measurements is provided. Most of the prior work heavily relies on data-driven approaches to obtain solutions to at least one of the unknowns, and typically two, running with the risk of failing to generalize to unseen domains. The shape representations used in the prior work also mainly focus on point cloud and signed distance field (SDF). In stark contrast to the prior work, we approach the problem using an iterative estimation method that does not require learning from pose-annotated data. In addition, we adopt a novel mesh-based object active shape model that the previous literature has not explored. Our algorithm, ShapeICP, is based on the iterative closest point (ICP) algorithm but is equipped with additional features for the category-level pose and shape estimation task. Although not using pose-annotated data, ShapeICP surpasses many data-driven approaches that rely on pose data for training, opening up a new solution space for researchers to consider.
Authors: Bojun Xiong, Si-Tong Wei, Xin-Yang Zheng, Yan-Pei Cao, Zhouhui Lian, Peng-Shuai Wang
Abstract: Diffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are guaranteed to be continuous and manifold. The key components of OctFusion are the octree-based latent representation and the accompanying diffusion models. The representation combines the benefits of both implicit neural representations and explicit spatial octrees and is learned with an octree-based variational autoencoder. The proposed diffusion model is a unified multi-scale U-Net that enables weights and computation sharing across different octree levels and avoids the complexity of widely used cascaded diffusion schemes. We verify the effectiveness of OctFusion on the ShapeNet and Objaverse datasets and achieve state-of-the-art performances on shape generation tasks. We demonstrate that OctFusion is extendable and flexible by generating high-quality color fields for textured mesh generation and high-quality 3D shapes conditioned on text prompts, sketches, or category labels. Our code and pre-trained models are available at https://github.com/octree-nn/octfusion.
Authors: Muye Huang, Lingling Zhang, Lai Han, Wenjun Wu, Xinyu Zhang, Jun Liu
Abstract: Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to interpret, and chart-related questions often involve complex logical and numerical reasoning, which hinders the performance of existing models. This paper introduces VProChart, a novel framework designed to address these challenges in CQA by integrating a lightweight Visual Perception Alignment Agent (VPAgent) and a Programmatic Solution Reasoning approach. VPAgent aligns and models chart elements based on principles of human visual perception, enhancing the understanding of chart context. The Programmatic Solution Reasoning approach leverages large language models (LLMs) to transform natural language reasoning questions into structured solution programs, facilitating precise numerical and logical reasoning. Extensive experiments on benchmark datasets such as ChartQA and PlotQA demonstrate that VProChart significantly outperforms existing methods, highlighting its capability in understanding and reasoning with charts.
Authors: Nour Shaheen, Tamer Elsharnouby, Marwan Torki
Abstract: In scientific research, charts are usually the primary method for visually representing data. However, the accessibility of charts remains a significant concern. In an effort to improve chart understanding pipelines, we focus on optimizing the chart classification component. We leverage curriculum learning, which is inspired by the human learning process. In this paper, we introduce a novel training approach for chart classification that utilizes coarse-to-fine curriculum learning. Our approach, which we name C2F-CHART (for coarse-to-fine) exploits inter-class similarities to create learning tasks of varying difficulty levels. We benchmark our method on the ICPR 2022 CHART-Infographics UB UNITEC PMC dataset, outperforming the state-of-the-art results.
Authors: Jian Yang, Xukun Wang, Wentao Wang, Guoming Li, Qihang Fang, Ruihong Yuan, Tianyang Wang, Xiaomei Zhang, Yeying Jin, Zhaoxin Fan
Abstract: Audio-driven IDentity-specific Talking Head Generation (ID-specific THG) has shown increasing promise for applications in filmmaking and virtual reality. Existing approaches are generally constructed as end-to-end paradigms, and have achieved significant progress. However, they often struggle to capture high-frequency textures due to limited model capacity. To address these limitations, we adopt a simple yet efficient post-processing framework -- unlike previous studies that focus solely on end-to-end training -- guided by our theoretical insights. Specifically, leveraging the \textit{Lipschitz Continuity Theory} of neural networks, we prove a crucial noise tolerance property for the Vector Quantized AutoEncoder (VQ-AE), and establish the existence of a Noise Robustness Upper Bound (NRoUB). This insight reveals that we can efficiently obtain an identity-specific denoiser by training an identity-specific neural discrete representation, without requiring an extra network. Based on this theoretical foundation, we propose a plug-and-play Space-Optimized VQ-AE (SOVQAE) with enhanced NRoUB to achieve temporally-consistent denoising. For practical deployment, we further introduce a cascade pipeline combining a pretrained Wav2Lip model with SOVQAE to perform ID-specific THG. Our experiments demonstrate that this pipeline achieves \textit{state-of-the-art} performance in video quality and robustness for out-of-distribution lip synchronization, surpassing existing identity-specific THG methods. In addition, the pipeline requires only a couple of consumer GPU hours and runs in real time, which is both efficient and practical for industry applications.
Authors: Zhiyu Zhu, Jinhui Hou, Hui Liu, Huanqiang Zeng, Junhui Hou
Abstract: The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e.g., low-quality images or a Gaussian distribution. In this paper, we reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency. Initially, we navigate effective restoration paths through a reinforcement learning process, gradually steering potential trajectories toward the most precise options. Additionally, to mitigate the considerable computational burden associated with iterative sampling, we propose cost-aware trajectory distillation to streamline complex paths into several manageable steps with adaptable sizes. Moreover, we fine-tune a foundational diffusion model (FLUX) with 12B parameters by using our algorithms, producing a unified framework for handling 7 kinds of image restoration tasks. Extensive experiments showcase the $\textit{significant}$ superiority of the proposed method, achieving a maximum PSNR improvement of 2.1 dB over state-of-the-art methods, while also greatly enhancing visual perceptual quality. Project page: https://zhu-zhiyu.github.io/FLUX-IR/.
Authors: Hrishav Bakul Barua, Kalin Stefanov, Lemuel Lai En Che, Abhinav Dhall, KokSheik Wong, Ganesh Krishnasamy
Abstract: The translation of Low Dynamic Range (LDR) to High Dynamic Range (HDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR,HDR} datasets for model training. In addition, there is limited literature on using unpaired datasets for this task, that is, the model learns a mapping between domains, i.e., {LDR,HDR}. This paper proposes LLM-HDR, a method that integrates the perception of Large Language Models (LLM) into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired {LDR,HDR} datasets for training. The method introduces novel artifact- and exposure-aware generators to address visual artifact removal and an encoder and loss to address semantic consistency, another under-explored topic. LLM-HDR is the first to use an LLM for the {LDR,HDR} translation task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/LLM-HDR
Authors: Jan Sellner, Alexander Studier-Fischer, Ahmad Bin Qasim, Silvia Seidlitz, Nicholas Schreck, Minu Tizabi, Manuel Wiesenfarth, Annette Kopp-Schneider, Janne Heinecke, Jule Brandt, Samuel Kn\"odler, Caelan Max Haney, Gabriel Salg, Berkin \"Ozdemir, Maximilian Dietrich, Maurice Stephan Michel, Felix Nickel, Karl-Friedrich Kowalewski, Lena Maier-Hein
Abstract: Novel optical imaging techniques, such as hyperspectral imaging (HSI) combined with machine learning-based (ML) analysis, have the potential to revolutionize clinical surgical imaging. However, these novel modalities face a shortage of large-scale, representative clinical data for training ML algorithms, while preclinical animal data is abundantly available through standardized experiments and allows for controlled induction of pathological tissue states, which is not ethically possible in patients. To leverage this situation, we propose a novel concept called "xeno-learning", a cross-species knowledge transfer paradigm inspired by xeno-transplantation, where organs from a donor species are transplanted into a recipient species. Using a total of 13,874 HSI images from humans as well as porcine and rat models, we show that although spectral signatures of organs differ substantially across species, relative changes resulting from pathologies or surgical manipulation (e.g., malperfusion; injection of contrast agent) are comparable. Such changes learnt in one species can thus be transferred to a new species via a novel "physiology-based data augmentation" method, enabling the large-scale secondary use of preclinical animal data for humans. The resulting ethical, monetary, and performance benefits promise a high impact of the proposed knowledge transfer paradigm on future developments in the field.
Authors: Yiming Ji, Kaijie Yun, Yang Liu, Zhengpu Wang, Boyu Ma, Zongwu Xie, Hong Liu
Abstract: The Object Navigation (ObjectNav) task aims to guide an agent to locate target objects in unseen environments using partial observations. Prior approaches have employed location prediction paradigms to achieve long-term goal reasoning, yet these methods often struggle to effectively integrate contextual relation reasoning. Alternatively, map completion-based paradigms predict long-term goals by generating semantic maps of unexplored areas. However, existing methods in this category fail to fully leverage known environmental information, resulting in suboptimal map quality that requires further improvement. In this work, we propose a novel approach to enhancing the ObjectNav task, by training a diffusion model to learn the statistical distribution patterns of objects in semantic maps, and using the map of the explored regions during navigation as the condition to generate the map of the unknown regions, thereby realizing the long-term goal reasoning of the target object, i.e., diffusion as reasoning (DAR). Meanwhile, we propose the Room Guidance method, which leverages commonsense knowledge derived from large language models (LLMs) to guide the diffusion model in generating room-aware object distributions. Based on the generated map in the unknown region, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson and MP3D show the effectiveness of our method.
Authors: Quan Zhang, Jinwei Fang, Rui Yuan, Xi Tang, Yuxin Qi, Ke Zhang, Chun Yuan
Abstract: Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Models(LLMs) has proven instrumental in constructing robust video understanding systems, effectively surmounting constraints associated with predefined visual tasks. These sophisticated MLLMs exhibit remarkable proficiency in comprehending videos, swiftly attaining unprecedented performance levels across diverse benchmarks. However, their operation demands substantial memory and computational resources, underscoring the continued importance of traditional models in video comprehension tasks. In this paper, we introduce a novel learning paradigm termed MLLM4WTAL. This paradigm harnesses the potential of MLLM to offer temporal action key semantics and complete semantic priors for conventional Weakly-supervised Temporal Action Localization (WTAL) methods. MLLM4WTAL facilitates the enhancement of WTAL by leveraging MLLM guidance. It achieves this by integrating two distinct modules: Key Semantic Matching (KSM) and Complete Semantic Reconstruction (CSR). These modules work in tandem to effectively address prevalent issues like incomplete and over-complete outcomes common in WTAL methods. Rigorous experiments are conducted to validate the efficacy of our proposed approach in augmenting the performance of various heterogeneous WTAL models.
Authors: Xudong Yan, Songhe Feng, Yang Zhang, Jian Yang, Yueguan Lin, Haojun Fei
Abstract: Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attributes and objects by extracting shared and exclusive parts between the image pair sharing the same attribute (object), as well as aligning them with pretrained word embeddings to improve unseen attribute-object recognition. Despite the significant achievements of existing efforts, they are hampered by three limitations: (1) The efficacy of disentanglement is compromised due to the influence of the background and the intricate entanglement of attributes with objects in the same parts. (2) Existing word embeddings fail to capture complex multimodal semantic information. (3) Overconfidence exhibited by existing models in seen compositions hinders their generalization to novel compositions. Being aware of these, we propose a novel framework named multimodal large language model (MLLM) embeddings and attribute smoothing guided disentanglement for CZSL. First, we leverage feature adaptive aggregation modules to mitigate the impact of background, and utilize learnable condition masks to capture multi-granularity features for disentanglement. Moreover, the last hidden states of MLLM are employed as word embeddings for their superior representation capabilities. Furthermore, we propose attribute smoothing with auxiliary attributes generated by the large language model (LLM) for seen compositions to address the overconfidence challenge. Extensive experiments demonstrate that our method achieves state-of-the-art performance on three challenging datasets. The source code will be available at https://github.com/xud-yan/Trident .
Authors: Minghao Fu, Hao Yu, Jie Shao, Junjie Zhou, Ke Zhu, Jianxin Wu
Abstract: Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration technique, reduces storage costs and enables potential inference acceleration by discretizing network weights and activations into a finite set of integer values. However, current quantization methods are often complex and sensitive, requiring extensive task-specific hyperparameters, where even a single misconfiguration can impair model performance, limiting generality across different models and tasks. In this paper, we propose Quantization without Tears (QwT), a method that simultaneously achieves quantization speed, accuracy, simplicity, and generality. The key insight of QwT is to incorporate a lightweight additional structure into the quantized network to mitigate information loss during quantization. This structure consists solely of a small set of linear layers, keeping the method simple and efficient. More importantly, it provides a closed-form solution, allowing us to improve accuracy effortlessly under 2 minutes. Extensive experiments across various vision, language, and multimodal tasks demonstrate that QwT is both highly effective and versatile. In fact, our approach offers a robust solution for network quantization that combines simplicity, accuracy, and adaptability, which provides new insights for the design of novel quantization paradigms. The code is publicly available at https://github.com/wujx2001/QwT
Authors: Guanyu Zhou, Wenxuan Liu, Wenxin Huang, Xuemei Jia, Xian Zhong, Chia-Wen Lin
Abstract: The lack of occlusion data in common action recognition video datasets limits model robustness and hinders consistent performance gains. We build OccludeNet, a large-scale occluded video dataset including both real and synthetic occlusion scenes in different natural settings. OccludeNet includes dynamic occlusion, static occlusion, and multi-view interactive occlusion, addressing gaps in current datasets. Our analysis shows occlusion affects action classes differently: actions with low scene relevance and partial body visibility see larger drops in accuracy. To overcome the limits of existing occlusion-aware methods, we propose a structural causal model for occluded scenes and introduce the Causal Action Recognition (CAR) method, which uses backdoor adjustment and counterfactual reasoning. This approach strengthens key actor information and improves model robustness to occlusion. We hope the challenges of OccludeNet will encourage more study of causal links in occluded scenes and lead to a fresh look at class relations, ultimately leading to lasting performance improvements. Our code and data is availibale at: https://github.com/The-Martyr/OccludeNet-Dataset
Authors: Haojie Zhang, Zhihao Liang, Ruibo Fu, Bingyan Liu, Zhengqi Wen, Xuefei Liu, Chenxing Li, Yaling Liang
Abstract: Portrait image animation using audio has rapidly advanced, but challenges remain in efficiently fusing multimodal inputs while ensuring temporal and portrait consistency with minimal computational cost. To address this, we present LetsTalk, a LinEar diffusion TranSformer for Talking video synthesis. LetsTalk incorporates a deep compression autoencoder to obtain efficient latent representations, and a spatio-temporal-aware transformer with efficient linear attention to effectively fuse multimodal information and enhance spatio-temporal consistency. We systematically explore and summarize three fusion schemes, ranging from shallow to deep fusion. We thoroughly analyze their characteristics, applicability, and trade-offs, thereby bridging critical gaps in multimodal conditional guidance. Based on modality differences of image, audio, and video generation, we adopt deep (Symbiotic Fusion) for portrait to ensure consistency, and shallow (Direct Fusion) for audio to align animation with speech while preserving motion diversity. To maintain temporal consistency in long-duration video generation, we propose a memory bank mechanism that preserves inter-clip dependencies, effectively preventing degradation across extended sequences. Furthermore, we develop a noise-regularized training strategy that explicitly compensates for DDPM sampling artifacts, significantly improving the model's robustness in continuous generation scenarios.Our extensive experiments demonstrate that our approach achieves state-of-the-art generation quality, producing temporally coherent and realistic videos with enhanced diversity and liveliness, while maintaining remarkable efficiency through its optimized model design with 8$\times$ fewer parameters.
Authors: Zhiqiang Shen, Ammar Sherif, Zeyuan Yin, Shitong Shao
Abstract: Recent advances in dataset distillation have led to solutions in two main directions. The conventional batch-to-batch matching mechanism is ideal for small-scale datasets and includes bi-level optimization methods on models and syntheses, such as FRePo, RCIG, and RaT-BPTT, as well as other methods like distribution matching, gradient matching, and weight trajectory matching. Conversely, batch-to-global matching typifies decoupled methods, which are particularly advantageous for large-scale datasets. This approach has garnered substantial interest within the community, as seen in SRe$^2$L, G-VBSM, WMDD, and CDA. A primary challenge with the second approach is the lack of diversity among syntheses within each class since samples are optimized independently and the same global supervision signals are reused across different synthetic images. In this study, we propose a new Diversity-driven EarlyLate Training (DELT) scheme to enhance the diversity of images in batch-to-global matching with less computation. Our approach is conceptually simple yet effective, it partitions predefined IPC samples into smaller subtasks and employs local optimizations to distill each subset into distributions from distinct phases, reducing the uniformity induced by the unified optimization process. These distilled images from the subtasks demonstrate effective generalization when applied to the entire task. We conduct extensive experiments on CIFAR, Tiny-ImageNet, ImageNet-1K, and its sub-datasets. Our approach outperforms the previous state-of-the-art by 2$\sim$5% on average across different datasets and IPCs (images per class), increasing diversity per class by more than 5% while reducing synthesis time by up to 39.3% for enhancing the training efficiency. Code is available at: https://github.com/VILA-Lab/DELT.
Authors: Chancharik Mitra, Brandon Huang, Tianning Chai, Zhiqiu Lin, Assaf Arbelle, Rogerio Feris, Leonid Karlinsky, Trevor Darrell, Deva Ramanan, Roei Herzig
Abstract: Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e., tasks with vision-language inputs and discrete labels) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for these tasks is the extraction of useful features from generative LMMs. To overcome this, we propose an approach that leverages multimodal feature extraction from the LMM's latent space. Toward this end, we present Sparse Attention Vectors (SAVs) -- a finetuning-free method that leverages sparse attention head activations (fewer than 5% of the heads) in LMMs as strong feature representations. With only few-shot examples, SAVs demonstrate state-of-the-art performance compared to a variety of few-shot and finetuned baselines on a collection of vision-language classification tasks. Our experiments also imply that SAVs can scale in performance with additional examples and generalize to similar tasks, establishing SAVs as both effective and robust multimodal feature representations.
Authors: Fawad Javed Fateh, Umer Ahmed, Hamza Khan, M. Zeeshan Zia, Quoc-Huy Tran
Abstract: This paper introduces TemporalVLM, a video large language model (video LLM) capable of effective temporal reasoning and fine-grained understanding in long videos. At the core, our approach includes a visual encoder for mapping a long-term input video into features which are time-aware and contain both local and global cues. In particular, it first divides the input video into short-term clips, which are jointly encoded with their timestamps into time-sensitive local features. Next, the local features are passed through a bidirectional long short-term memory (BiLSTM) module for global feature aggregation. The extracted time-aware and multi-level features are important for accurate temporal reasoning and fine-grained understanding in long videos. Moreover, to facilitate the evaluation of TemporalVLM, we present a large-scale long video dataset of industry assembly processes, namely IndustryASM, which consists of videos recorded on factory floors with actions and timestamps annotated by industrial engineers for time and motion studies and temporal action segmentation evaluation. Finally, extensive experiments on datasets of long videos, including TimeIT and IndustryASM, show that TemporalVLM achieves superior performance than previous methods across temporal reasoning and fine-grained understanding tasks, namely dense video captioning, temporal video grounding, video highlight detection, and temporal action segmentation. To the best of our knowledge, our work is the first to incorporate LSTMs into video LLMs.
Authors: Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy, Runfeng Li, Leonidas Guibas, James Tompkin, Adam W. Harley
Abstract: Gaussian splatting methods are emerging as a popular approach for converting multi-view image data into scene representations that allow view synthesis. In particular, there is interest in enabling view synthesis for dynamic scenes using only monocular input data -- an ill-posed and challenging problem. The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true. In this work, we organize, benchmark, and analyze many Gaussian-splatting-based methods, providing apples-to-apples comparisons that prior works have lacked. We use multiple existing datasets and a new instructive synthetic dataset designed to isolate factors that affect reconstruction quality. We systematically categorize Gaussian splatting methods into specific motion representation types and quantify how their differences impact performance. Empirically, we find that their rank order is well-defined in synthetic data, but the complexity of real-world data currently overwhelms the differences. Furthermore, the fast rendering speed of all Gaussian-based methods comes at the cost of brittleness in optimization. We summarize our experiments into a list of findings that can help to further progress in this lively problem setting.
Authors: Daoyi Gao, Yawar Siddiqui, Lei Li, Angela Dai
Abstract: Articulated 3D object generation is fundamental for creating realistic, functional, and interactable virtual assets which are not simply static. We introduce MeshArt, a hierarchical transformer-based approach to generate articulated 3D meshes with clean, compact geometry, reminiscent of human-crafted 3D models. We approach articulated mesh generation in a part-by-part fashion across two stages. First, we generate a high-level articulation-aware object structure; then, based on this structural information, we synthesize each part's mesh faces. Key to our approach is modeling both articulation structures and part meshes as sequences of quantized triangle embeddings, leading to a unified hierarchical framework with transformers for autoregressive generation. Object part structures are first generated as their bounding primitives and articulation modes; a second transformer, guided by these articulation structures, then generates each part's mesh triangles. To ensure coherency among generated parts, we introduce structure-guided conditioning that also incorporates local part mesh connectivity. MeshArt shows significant improvements over state of the art, with 57.1% improvement in structure coverage and a 209-point improvement in mesh generation FID.
Authors: Wenyu Zhang, Wei En Ng, Lixin Ma, Yuwen Wang, Junqi Zhao, Allison Koenecke, Boyang Li, Lu Wang
Abstract: Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework supported by a new human-annotated dataset. SPHERE systematically probes models across increasing levels of complexity, from fundamental skills to multi-skill integration and high-level reasoning that combines spatial, visual, and logical understanding. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity, understanding both egocentric and allocentric perspectives, and applying spatial logic in physical contexts. These findings expose critical blind spots in existing models and underscore the need for more advanced spatial reasoning techniques, driving the development of vision-language models that align more closely with human spatial cognition. The SPHERE benchmark is available at https://github.com/zwenyu/SPHERE-VLM.
Authors: James E. Gallagher, Edward J. Oughton
Abstract: This paper presents the Visual Optical Recognition Telemetry EXtraction (VORTEX) system for extracting and analyzing drone telemetry data from First Person View (FPV) Uncrewed Aerial System (UAS) footage. VORTEX employs MMOCR, a PyTorch-based Optical Character Recognition (OCR) toolbox, to extract telemetry variables from drone Heads Up Display (HUD) recordings, utilizing advanced image preprocessing techniques, including CLAHE enhancement and adaptive thresholding. The study optimizes spatial accuracy and computational efficiency through systematic investigation of temporal sampling rates (1s, 5s, 10s, 15s, 20s) and coordinate processing methods. Results demonstrate that the 5-second sampling rate, utilizing 4.07% of available frames, provides the optimal balance with a point retention rate of 64% and mean speed accuracy within 4.2% of the 1-second baseline while reducing computational overhead by 80.5%. Comparative analysis of coordinate processing methods reveals that while UTM Zone 33N projection and Haversine calculations provide consistently similar results (within 0.1% difference), raw WGS84 coordinates underestimate distances by 15-30% and speeds by 20-35%. Altitude measurements showed unexpected resilience to sampling rate variations, with only 2.1% variation across all intervals. This research is the first of its kind, providing quantitative benchmarks for establishing a robust framework for drone telemetry extraction and analysis using open-source tools and spatial libraries.
Authors: Maxence Boels, Yang Liu, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin
Abstract: While existing approaches excel at recognising current surgical phases, they provide limited foresight and intraoperative guidance into future procedural steps. Similarly, current anticipation methods are constrained to predicting short-term and single events, neglecting the dense, repetitive, and long sequential nature of surgical workflows. To address these needs and limitations, we propose SWAG (Surgical Workflow Anticipative Generation), a framework that combines phase recognition and anticipation using a generative approach. This paper investigates two distinct decoding methods - single-pass (SP) and auto-regressive (AR) - to generate sequences of future surgical phases at minute intervals over long horizons. We propose a novel embedding approach using class transition probabilities to enhance the accuracy of phase anticipation. Additionally, we propose a generative framework using remaining time regression to classification (R2C). SWAG was evaluated on two publicly available datasets, Cholec80 and AutoLaparo21. Our single-pass model with class transition probability embeddings (SP*) achieves 32.1% and 41.3% F1 scores over 20 and 30 minutes on Cholec80 and AutoLaparo21, respectively. Moreover, our approach competes with existing methods on phase remaining time regression, achieving weighted mean absolute errors of 0.32 and 0.48 minutes for 2- and 3-minute horizons. SWAG demonstrates versatility across generative decoding frame works and classification and regression tasks to create temporal continuity between surgical workflow recognition and anticipation. Our method provides steps towards intraoperative surgical workflow generation for anticipation. Project: https://maxboels.github.io/swag.
Authors: Phi Vu Tran
Abstract: While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object classes follow a natural long-tailed distribution. Existing methods for long-tailed detection resort to external ImageNet labels to augment the low-shot training instances. However, such dependency on a large labeled database has limited utility in practical scenarios. We propose a versatile and scalable approach to leverage optional unlabeled images, which are easy to collect without the burden of human annotations. Our SimLTD framework is straightforward and intuitive, and consists of three simple steps: (1) pre-training on abundant head classes; (2) transfer learning on scarce tail classes; and (3) fine-tuning on a sampled set of both head and tail classes. Our approach can be viewed as an improved head-to-tail model transfer paradigm without the added complexities of meta-learning or knowledge distillation, as was required in past research. By harnessing supplementary unlabeled images, without extra image labels, SimLTD establishes new record results on the challenging LVIS v1 benchmark across both supervised and semi-supervised settings.
Authors: Yuchuan Tian, Jing Han, Chengcheng Wang, Yuchen Liang, Chao Xu, Hanting Chen
Abstract: Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their reliance on complicated self-attention operation results in slow inference speeds. Contrary to these works, we rethink one of the simplest yet fastest module in deep learning, 3x3 Convolution, to construct a scaled-up purely convolutional diffusion model. We first discover that an Encoder-Decoder Hourglass design outperforms scalable isotropic architectures for Conv3x3, but still under-performing our expectation. Further improving the architecture, we introduce sparse skip connections to reduce redundancy and improve scalability. Based on the architecture, we introduce conditioning improvements including stage-specific embeddings, mid-block condition injection, and conditional gating. These improvements lead to our proposed Diffusion CNN (DiC), which serves as a swift yet competitive diffusion architecture baseline. Experiments on various scales and settings show that DiC surpasses existing diffusion transformers by considerable margins in terms of performance while keeping a good speed advantage. Project page: https://github.com/YuchuanTian/DiC
Authors: Hongyuan Dong, Zijian Kang, Weijie Yin, Xiao Liang, Chao Feng, Jiao Ran
Abstract: In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) series achieving state-of-the-art (SOTA) performance in 2B and 8B parameters. The following three key improvements contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a data construction pipeline to enable hundred-million-scale high-quality recaption data annotation. The resulted dataset SAIL-Caption is validated to be of the highest data quality compared with opensource datasets. (2) Scalable Pretraining with High-Quality Visual Understanding Data: We scale SAIL-VL's pretraining budget up to 655B tokens and show that even a 2B VLM benefits from scaled up training data sizes, exhibiting logarithmic data size scaling laws in benchmark performance. (3) Scalable SFT via data quantity and complexity scaling: We curate a high-quality SFT dataset collection with leading data quantity scaling effectiveness and demonstrate that training with progressively higher-complexity data surpasses baseline one-stage training by a large margin. SAIL-VL series models achieve the highest average score in 18 widely used VLM benchmarks in our evaluation, with the 2B model takes the top position over VLMs of comparable sizes on OpenCompass 2024 (https://rank.opencompass.org.cn/leaderboard-multimodal), demonstrating robust visual comprehension abilities. SAIL-VL series models are released at HuggingFace (https://huggingface.co/BytedanceDouyinContent).
URLs: https://rank.opencompass.org.cn/leaderboard-multimodal),, https://huggingface.co/BytedanceDouyinContent).
Authors: Junfei Xiao, Feng Cheng, Lu Qi, Liangke Gui, Jiepeng Cen, Zhibei Ma, Alan Yuille, Lu Jiang
Abstract: Recent video generation models have shown promising results in producing high-quality video clips lasting several seconds. However, these models face challenges in generating long sequences that convey clear and informative events, limiting their ability to support coherent narrations. In this paper, we present a large-scale cooking video dataset designed to advance long-form narrative generation in the cooking domain. We validate the quality of our proposed dataset in terms of visual fidelity and textual caption accuracy using state-of-the-art Vision-Language Models (VLMs) and video generation models, respectively. We further introduce a Long Narrative Video Director to enhance both visual and semantic coherence in generated videos and emphasize the role of aligning visual embeddings to achieve improved overall video quality. Our method demonstrates substantial improvements in generating visually detailed and semantically aligned keyframes, supported by finetuning techniques that integrate text and image embeddings within the video generation process. Project page: https://videoauteur.github.io/
Authors: Alper Kayabasi, Anil Kumar Vadathya, Guha Balakrishnan, Vishwanath Saragadam
Abstract: We propose a new continuous video modeling framework based on implicit neural representations (INRs) called ActINR. At the core of our approach is the observation that INRs can be considered as a learnable dictionary, with the shapes of the basis functions governed by the weights of the INR, and their locations governed by the biases. Given compact non-linear activation functions, we hypothesize that an INR's biases are suitable to capture motion across images, and facilitate compact representations for video sequences. Using these observations, we design ActINR to share INR weights across frames of a video sequence, while using unique biases for each frame. We further model the biases as the output of a separate INR conditioned on time index to promote smoothness. By training the video INR and this bias INR together, we demonstrate unique capabilities, including $10\times$ video slow motion, 4x spatial super resolution along with 2x slow motion, denoising, and video inpainting. ActINR performs remarkably well across numerous video processing tasks (often achieving more than 6dB improvement), setting a new standard for continuous modeling of videos.
Authors: Hongxin Li, Jingfan Chen, Jingran Su, Yuntao Chen, Qing Li, Zhaoxiang Zhang
Abstract: User interface understanding with vision-language models (VLMs) has received much attention due to its potential for enhancing software automation. However, existing datasets used to build UI-VLMs either only contain large-scale context-free element annotations or contextualized functional descriptions for elements at a small scale. In this work, we propose the \textbf{AutoGUI} pipeline for automatically annotating UI elements with detailed functionality descriptions at scale. Specifically, we leverage large language models (LLMs) to infer element functionality by comparing UI state changes before and after simulated interactions. To improve annotation quality, we propose LLM-aided rejection and verification, eliminating invalid annotations without human labor. We construct a high-quality AutoGUI-704k dataset using the proposed pipeline, featuring diverse and detailed functionality annotations that are hardly provided by previous datasets. Human evaluation shows that we achieve annotation correctness comparable to a trained human annotator. Extensive experiments show that our dataset remarkably enhances VLM's UI grounding capabilities and exhibits significant scaling effects. We also show the interesting potential use of our dataset in UI agent tasks. Please view our project at https://autogui-project.github.io/.
Authors: Minh-Quan Le, Gaurav Mittal, Tianjian Meng, A S M Iftekhar, Vishwas Suryanarayanan, Barun Patra, Dimitris Samaras, Mei Chen
Abstract: While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce $\textbf{Hummingbird}$, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the reference image while ensuring high fidelity by accurately preserving scene attributes, such as object interactions and spatial relationships from the text guidance. Hummingbird employs a novel Multimodal Context Evaluator that simultaneously optimizes our formulated Global Semantic and Fine-grained Consistency Rewards to ensure generated images preserve the scene attributes of reference images in relation to the text guidance while maintaining diversity. As the first model to address the task of maintaining both diversity and fidelity given a multimodal context, we introduce a new benchmark formulation incorporating MME Perception and Bongard HOI datasets. Benchmark experiments show Hummingbird outperforms all existing methods by achieving superior fidelity while maintaining diversity, validating Hummingbird's potential as a robust multimodal context-aligned image generator in complex visual tasks. Project page: https://roar-ai.github.io/hummingbird
Authors: Wenjie Wei, Malu Zhang, Zijian Zhou, Ammar Belatreche, Yimeng Shan, Yu Liang, Honglin Cao, Jieyuan Zhang, Yang Yang
Abstract: Brain-inspired Spiking Neural Networks (SNNs) leverage sparse spikes to encode information and operate in an asynchronous event-driven manner, offering a highly energy-efficient paradigm for machine intelligence. However, the current SNN community focuses primarily on performance improvement by developing large-scale models, which limits the applicability of SNNs in resource-limited edge devices. In this paper, we propose a hardware-friendly and lightweight SNN, aimed at effectively deploying high-performance SNN in resource-limited scenarios. Specifically, we first develop a baseline model that integrates uniform quantization and structured pruning, called QP-SNN baseline. While this baseline significantly reduces storage demands and computational costs, it suffers from performance decline. To address this, we conduct an in-depth analysis of the challenges in quantization and pruning that lead to performance degradation and propose solutions to enhance the baseline's performance. For weight quantization, we propose a weight rescaling strategy that utilizes bit width more effectively to enhance the model's representation capability. For structured pruning, we propose a novel pruning criterion using the singular value of spatiotemporal spike activities to enable more accurate removal of redundant kernels. Extensive experiments demonstrate that integrating two proposed methods into the baseline allows QP-SNN to achieve state-of-the-art performance and efficiency, underscoring its potential for enhancing SNN deployment in edge intelligence computing.
Authors: Weijie Wang, Guofeng Mei, Jian Zhang, Nicu Sebe, Bruno Lepri, Fabio Poiesi
Abstract: Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem, by fusing information from coordinates and features at the super-point level between point clouds. This formulation has remained unexplored primarily because it must guarantee rotation and translation invariance since point clouds reside in different and independent reference frames. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds and account for their geometric structure. By doing so, points from two distinct point clouds can attend to each other under arbitrary rigid transformations. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching. Our formulation boosts the number of inlier correspondences, thereby yielding more precise registration results compared to state-of-the-art approaches. We have conducted an extensive evaluation on 3DMatch, 3DLoMatch, KITTI, and 3DCSR datasets.
Authors: Xingrui Wang, Wufei Ma, Tiezheng Zhang, Celso M de Melo, Jieneng Chen, Alan Yuille
Abstract: Although large multimodal models (LMMs) have demonstrated remarkable capabilities in visual scene interpretation and reasoning, their capacity for complex and precise 3-dimensional spatial reasoning remains uncertain. Existing benchmarks focus predominantly on 2D spatial understanding and lack a framework to comprehensively evaluate 6D spatial reasoning across varying complexities. To address this limitation, we present Spatial457, a scalable and unbiased synthetic dataset designed with 4 key capability for spatial reasoning: multi-object recognition, 2D location, 3D location, and 3D orientation. We develop a cascading evaluation structure, constructing 7 question types across 5 difficulty levels that range from basic single object recognition to our new proposed complex 6D spatial reasoning tasks. We evaluated various large multimodal models (LMMs) on PulseCheck457, observing a general decline in performance as task complexity increases, particularly in 3D reasoning and 6D spatial tasks. To quantify these challenges, we introduce the Relative Performance Dropping Rate (RPDR), highlighting key weaknesses in 3D reasoning capabilities. Leveraging the unbiased attribute design of our dataset, we also uncover prediction biases across different attributes, with similar patterns observed in real-world image settings. The code and data are released in https://github.com/XingruiWang/Spatial457.
Authors: Minghao Fu, Guo-Hua Wang, Liangfu Cao, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang
Abstract: Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their independent application in current text-to-image models continues to face significant challenges in achieving strong text-image alignment, high generation quality, and consistency with human aesthetic standards. In this work, we for the first time, explore facilitating the collaboration of human performance alignment and test-time sampling to unlock the potential of text-to-image models. Consequently, we introduce CHATS (Combining Human-Aligned optimization and Test-time Sampling), a novel generative framework that separately models the preferred and dispreferred distributions and employs a proxy-prompt-based sampling strategy to utilize the useful information contained in both distributions. We observe that CHATS exhibits exceptional data efficiency, achieving strong performance with only a small, high-quality funetuning dataset. Extensive experiments demonstrate that CHATS surpasses traditional preference alignment methods, setting new state-of-the-art across various standard benchmarks.
Authors: Ivan Skorokhodov, Sharath Girish, Benran Hu, Willi Menapace, Yanyu Li, Rameen Abdal, Sergey Tulyakov, Aliaksandr Siarohin
Abstract: Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements have primarily focused on scaling diffusion backbones and improving autoencoder reconstruction quality, the interaction between these components has received comparatively less attention. In this work, we perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces, which are especially pronounced in the autoencoders with a large bottleneck channel size. We hypothesize that this high-frequency component interferes with the coarse-to-fine nature of the diffusion synthesis process and hinders the generation quality. To mitigate the issue, we propose scale equivariance: a simple regularization strategy that aligns latent and RGB spaces across frequencies by enforcing scale equivariance in the decoder. It requires minimal code changes and only up to 20K autoencoder fine-tuning steps, yet significantly improves generation quality, reducing FID by 19% for image generation on ImageNet-1K $256^2$ and FVD by at least 44% for video generation on Kinetics-700 $17 \times 256^2$. The source code is available at https://github.com/snap-research/diffusability.
Authors: Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-Wei Chang, Heng Ji
Abstract: Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively.
Authors: Alexander Groshev, Anastasiia Iashchenko, Pavel Paramonov, Denis Dimitrov, Andrey Kuznetsov
Abstract: While the task of face swapping has recently gained attention in the research community, a related problem of head swapping remains largely unexplored. In addition to skin color transfer, head swap poses extra challenges, such as the need to preserve structural information of the whole head during synthesis and inpaint gaps between swapped head and background. In this paper, we address these concerns with GHOST 2.0, which consists of two problem-specific modules. First, we introduce enhanced Aligner model for head reenactment, which preserves identity information at multiple scales and is robust to extreme pose variations. Secondly, we use a Blender module that seamlessly integrates the reenacted head into the target background by transferring skin color and inpainting mismatched regions. Both modules outperform the baselines on the corresponding tasks, allowing to achieve state of the art results in head swapping. We also tackle complex cases, such as large difference in hair styles of source and target. Code is available at https://github.com/ai-forever/ghost-2.0
Authors: Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen
Abstract: Perceiving visual scenes as objects and background -- like humans do -- Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. OCL's self-supervision of reconstructing the input from these aggregated slots struggles with complex object textures, thus Vision Foundation Model (VFM) representations are used as the aggregation input and reconstruction target. However, existing methods leverage VFM representations in diverse ways and often fail to fully exploit their potential. In response, we propose a clean architecture -- Vector-Quantized VFMs for OCL (VQ-VFM-OCL, or VVO) -- that unifies mainstream OCL methods. The key to our unification is simple yet effective, just shared quantizing the same VFM representation as the reconstruction target. Through mathematical modeling and statistical verification, we further analyze why VFM representations facilitate OCL aggregation and how their shared quantization as reconstruction targets strengthens OCL supervision. Experiments show that across different VFMs, aggregators and decoders, our VVO consistently outperforms baselines in object discovery and recognition, as well as downstream visual prediction and reasoning. The implementation and model checkpoints are available on https://github.com/Genera1Z/VQ-VFM-OCL.
Authors: Ang Cao, Sergio Arnaud, Oleksandr Maksymets, Jianing Yang, Ayush Jain, Sriram Yenamandra, Ada Martin, Vincent-Pierre Berges, Paul McVay, Ruslan Partsey, Aravind Rajeswaran, Franziska Meier, Justin Johnson, Jeong Joon Park, Alexander Sax
Abstract: 3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance. We introduce $\textbf{LIFT-GS}$, a practical distillation technique that overcomes this limitation by using differentiable rendering to bridge 3D and 2D supervision. LIFT-GS predicts 3D Gaussian representations from point clouds and uses them to render predicted language-conditioned 3D masks into 2D views, enabling supervision from 2D foundation models (SAM, CLIP, LLaMA) without requiring any 3D annotations. This render-supervised formulation enables end-to-end training of complete encoder-decoder architectures and is inherently model-agnostic. LIFT-GS achieves state-of-the-art results with $25.7\%$ mAP on open-vocabulary instance segmentation (vs. $20.2\%$ prior SOTA) and consistent $10-30\%$ improvements on referential grounding tasks. Remarkably, pretraining effectively multiplies fine-tuning datasets by 2X, demonstrating strong scaling properties that suggest 3D VLG currently operates in a severely data-scarce regime. Project page: https://liftgs.github.io
URLs: https://liftgs.github.io
Authors: MohammadHossein Rezaei, Yicheng Fu, Phil Cuvin, Caleb Ziems, Yanzhe Zhang, Hao Zhu, Diyi Yang
Abstract: Human activity is moderated by norms; however, supervision for normative reasoning is sparse, particularly where norms are physically- or socially-grounded. We thus present EGONORMIA $\|\epsilon\|$, comprising 1,853 (200 for EGONORMIA-verified) multiple choice questions (MCQs) grounded within egocentric videos of human interactions, enabling the evaluation and improvement of normative reasoning in vision-language models (VLMs). EGONORMIA spans seven norm categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline to generate grounded MCQs from raw egocentric video. Our work demonstrates that current state-of-the-art VLMs lack robust grounded norm understanding, scoring a maximum of 66% on EGONORMIA and 68% on EGONORMIA-verified, with performance across norm categories indicating significant risks of safety and privacy when VLMs are used in real-world agents. We additionally explore methods for improving normative understanding, demonstrating that a naive retrieval-based generation (RAG) method using EGONORMIA can enhance normative reasoning in VLMs.
Authors: Yu Pan, Jiahao Chen, Bingrong Dai, Lin Wang, Yi Du, Jiao Liu
Abstract: In recent years, Diffusion Models (DMs) have demonstrated significant advances in the field of image generation. However, according to current research, DMs are vulnerable to backdoor attacks, which allow attackers to control the model's output by inputting data containing covert triggers, such as a specific visual patch or phrase. Existing defense strategies are well equipped to thwart such attacks through backdoor detection and trigger inversion because previous attack methods are constrained by limited input spaces and low-dimensional triggers. For example, visual triggers are easily observed by defenders, text-based or attention-based triggers are more susceptible to neural network detection. To explore more possibilities of backdoor attack in DMs, we propose Gungnir, a novel method that enables attackers to activate the backdoor in DMs through style triggers within input images. Our approach proposes using stylistic features as triggers for the first time and implements backdoor attacks successfully in image-to-image tasks by introducing Reconstructing-Adversarial Noise (RAN) and Short-Term Timesteps-Retention (STTR). Our technique generates trigger-embedded images that are perceptually indistinguishable from clean images, thus bypassing both manual inspection and automated detection neural networks. Experiments demonstrate that Gungnir can easily bypass existing defense methods. Among existing DM defense frameworks, our approach achieves a 0 backdoor detection rate (BDR). Our codes are available at https://github.com/paoche11/Gungnir.
Authors: Xiao Wang, Jingyun Hua, Weihong Lin, Yuanxing Zhang, Fuzheng Zhang, Jianlong Wu, Di Zhang, Liqiang Nie
Abstract: Recent Multi-modal Large Language Models (MLLMs) have made great progress in video understanding. However, their performance on videos involving human actions is still limited by the lack of high-quality data. To address this, we introduce a two-stage data annotation pipeline. First, we design strategies to accumulate videos featuring clear human actions from the Internet. Second, videos are annotated in a standardized caption format that uses human attributes to distinguish individuals and chronologically details their actions and interactions. Through this pipeline, we curate two datasets, namely HAICTrain and HAICBench. \textbf{HAICTrain} comprises 126K video-caption pairs generated by Gemini-Pro and verified for training purposes. Meanwhile, \textbf{HAICBench} includes 412 manually annotated video-caption pairs and 2,000 QA pairs, for a comprehensive evaluation of human action understanding. Experimental results demonstrate that training with HAICTrain not only significantly enhances human understanding abilities across 4 benchmarks, but can also improve text-to-video generation results. Both the HAICTrain and HAICBench are released at https://huggingface.co/datasets/KuaishouHAIC/HAIC.
Authors: Kevin Qinghong Lin, Mike Zheng Shou
Abstract: Human daily activities can be concisely narrated as sequences of routine events (e.g., turning off an alarm) in video streams, forming an event vocabulary. Motivated by this, we introduce VLog, a novel video understanding framework that define video narrations as vocabulary, going beyond the typical subword vocabularies in existing generative video-language models. Built on the lightweight language model GPT-2, VLog feature three key innovations: (i) A generative retrieval model, marrying language model's complex reasoning capabilities with contrastive retrieval's flexible upgrading over narration vocabulary. (ii) A hierarchical vocabulary derived from large-scale video narrations using our narration pair encoding algorithm, enabling efficient indexing of specific events (e.g., cutting a tomato) by identifying broader scenarios (e.g., kitchen) with expressive postfixes (e.g., by the left hand). (iii) A vocabulary update strategy leveraging generative models to extend the vocabulary for novel events encountered during inference. To validate our approach, we introduce VidCap-Eval, a development set requiring concise narrations with reasoning relationships (e.g., before and after). Experiments on EgoSchema, COIN, and HiREST further demonstrate the effectiveness of VLog, highlighting its ability to generate concise, contextually accurate, and efficient narrations, offering a novel perspective on video understanding. Codes are released at https://github.com/showlab/VLog.
Authors: Ayush Jain, Alexander Swerdlow, Yuzhou Wang, Sergio Arnaud, Ada Martin, Alexander Sax, Franziska Meier, Katerina Fragkiadaki
Abstract: Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based approaches. To further reduce the domain gap between 2D and 3D, we incorporate 2D-to-3D lifting strategies, enabling UniVLG to utilize 2D data to enhance 3D performance. With these innovations, our model achieves state-of-the-art performance across multiple 3D vision-language grounding tasks, demonstrating the potential of transferring advances from 2D vision-language learning to the data-constrained 3D domain. Furthermore, co-training on both 2D and 3D data enhances performance across modalities without sacrificing 2D capabilities. By removing the reliance on 3D mesh reconstruction and ground-truth object proposals, UniVLG sets a new standard for realistic, embodied-aligned evaluation. Code and additional visualizations are available at https://univlg.github.io .
URLs: https://univlg.github.io
Authors: Md Abu Bakr Siddique, Vaishnav Ramesh, Junliang Liu, Piyush Singh, Md Jahidul Islam
Abstract: The concept of waterbody style transfer remains largely unexplored in the underwater imaging and vision literature. Traditional image style transfer (STx) methods primarily focus on artistic and photorealistic blending, often failing to preserve object and scene geometry in images captured in high-scattering mediums such as underwater. The wavelength-dependent nonlinear attenuation and depth-dependent backscattering artifacts further complicate learning underwater image STx from unpaired data. This paper introduces UStyle, the first data-driven learning framework for transferring waterbody styles across underwater images without requiring prior reference images or scene information. We propose a novel depth-aware whitening and coloring transform (DA-WCT) mechanism that integrates physics-based waterbody synthesis to ensure perceptually consistent stylization while preserving scene structure. To enhance style transfer quality, we incorporate carefully designed loss functions that guide UStyle to maintain colorfulness, lightness, structural integrity, and frequency-domain characteristics, as well as high-level content in VGG and CLIP (contrastive language-image pretraining) feature spaces. By addressing domain-specific challenges, UStyle provides a robust framework for no-reference underwater image STx, surpassing state-of-the-art (SOTA) methods that rely solely on end-to-end reconstruction loss. Furthermore, we introduce the UF7D dataset, a curated collection of high-resolution underwater images spanning seven distinct waterbody styles, establishing a benchmark to support future research in underwater image STx. The UStyle inference pipeline and UF7D dataset are released at: https://github.com/uf-robopi/UStyle.
Authors: Xiao Wang, Qingyi Si, Jianlong Wu, Shiyu Zhu, Li Cao, Liqiang Nie
Abstract: Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows that redundancy varies significantly across time and model layers, necessitating a more flexible compression strategy. We propose AdaReTaKe, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees. Integrated into state-of-the-art MLLMs, AdaReTaKe improves processing capacity from 256 to 2048 frames while preserving critical information. Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively, with even greater improvements of 5.9% and 6.0% on the longest LVBench. Our code is available at https://github.com/SCZwangxiao/video-FlexReduc.git.
Authors: Yihong Luo, Tianyang Hu, Weijian Luo, Kenji Kawaguchi, Jing Tang
Abstract: This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective integration of reward feedback for improved abilities like controllability and preference alignment remains a key open problem. Existing reward-guided post-training approaches targeting accelerated few-step generation often deem diffusion distillation losses indispensable. However, in this paper, we identify an interesting yet fundamental paradigm shift: as conditions become more specific, well-designed reward functions emerge as the primary driving force in training strong, few-step image generative models. Motivated by this insight, we introduce Reward-Instruct, a novel and surprisingly simple reward-centric approach for converting pre-trained base diffusion models into reward-enhanced few-step generators. Unlike existing methods, Reward-Instruct does not rely on expensive yet tricky diffusion distillation losses. Instead, it iteratively updates the few-step generator's parameters by directly sampling from a reward-tilted parameter distribution. Such a training approach entirely bypasses the need for expensive diffusion distillation losses, making it favorable to scale in high image resolutions. Despite its simplicity, Reward-Instruct yields surprisingly strong performance. Our extensive experiments on text-to-image generation have demonstrated that Reward-Instruct achieves state-of-the-art results in visual quality and quantitative metrics compared to distillation-reliant methods, while also exhibiting greater robustness to the choice of reward function.
Authors: Peipeng Yu, Jianwei Fei, Hui Gao, Xuan Feng, Zhihua Xia, Chip Hong Chang
Abstract: Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake detection due to the misalignment of their knowledge and forensics patterns. To this end, we present a novel framework that unlocks LVLMs' potential capabilities for deepfake detection. Our framework includes a Knowledge-guided Forgery Detector (KFD), a Forgery Prompt Learner (FPL), and a Large Language Model (LLM). The KFD is used to calculate correlations between image features and pristine/deepfake image description embeddings, enabling forgery classification and localization. The outputs of the KFD are subsequently processed by the Forgery Prompt Learner to construct fine-grained forgery prompt embeddings. These embeddings, along with visual and question prompt embeddings, are fed into the LLM to generate textual detection responses. Extensive experiments on multiple benchmarks, including FF++, CDF2, DFD, DFDCP, DFDC, and DF40, demonstrate that our scheme surpasses state-of-the-art methods in generalization performance, while also supporting multi-turn dialogue capabilities.
Authors: Weijie Guo, Guofeng Zhang, Wufei Ma, Alan Yuille
Abstract: Category-level 3D/6D pose estimation is a crucial step towards comprehensive 3D scene understanding, which would enable a broad range of applications in robotics and embodied AI. Recent works explored neural mesh models that approach a range of 2D and 3D tasks from an analysis-by-synthesis perspective. Despite the largely enhanced robustness to partial occlusion and domain shifts, these methods depended heavily on 3D annotations for part-contrastive learning, which confines them to a narrow set of categories and hinders efficient scaling. In this work, we present DINeMo, a novel neural mesh model that is trained with no 3D annotations by leveraging pseudo-correspondence obtained from large visual foundation models. We adopt a bidirectional pseudo-correspondence generation method, which produce pseudo correspondence utilize both local appearance features and global context information. Experimental results on car datasets demonstrate that our DINeMo outperforms previous zero- and few-shot 3D pose estimation by a wide margin, narrowing the gap with fully-supervised methods by 67.3%. Our DINeMo also scales effectively and efficiently when incorporating more unlabeled images during training, which demonstrate the advantages over supervised learning methods that rely on 3D annotations. Our project page is available at https://analysis-by-synthesis.github.io/DINeMo/.
Authors: Chi-Hsi Kung, Frangil Ramirez, Juhyung Ha, Yi-Ting Chen, David Crandall, Yi-Hsuan Tsai
Abstract: Understanding a procedural activity requires modeling both how action steps transform the scene and how evolving scene transformations can influence the sequence of action steps, even those that are accidental or erroneous. Existing work has studied procedure-aware video representations by proposing novel approaches such as modeling the temporal order of actions, and has not explicitly learned the state changes (scene transformations). In this work, we study procedure-aware video representation learning by incorporating state-change descriptions generated by Large Language Models (LLMs) as supervision signals for video encoders. Moreover, we generate state-change counterfactuals that simulate hypothesized failure outcomes, allowing models to learn by imagining the unseen ``What if'' scenarios. This counterfactual reasoning facilitates the model's ability to understand the cause and effect of each step in an activity. To verify the procedure awareness of our model, we conduct extensive experiments on procedure-aware tasks, including temporal action segmentation, error detection, action phase classification, frame retrieval, multi-instance retrieval, and action recognition. Our results demonstrate the effectiveness of the proposed state-change descriptions and their counterfactuals, and achieve significant improvements on multiple tasks. We will make our source code and data publicly available soon.
Authors: Hoigi Seo, Junseo Bang, Haechang Lee, Joohoon Lee, Byung Hyun Lee, Se Young Chun
Abstract: Text-to-image (T2I) models often suffer from text-image misalignment in complex scenes involving multiple objects and attributes. Semantic binding has attempted to associate the generated attributes and objects with their corresponding noun phrases (NPs) by text or latent optimizations with the modulation of cross-attention (CA) maps; yet, the factors that influence semantic binding remain underexplored. Here, we investigate the geometrical properties of text token embeddings and their CA maps. We found that the geometrical properties of token embeddings, specifically angular distances and norms, are crucial factors in the differentiation of the CA map. These theoretical findings led to our proposed training-free text-embedding-aware T2I framework, dubbed \textbf{TokeBi}, for strong semantic binding. TokeBi consists of Causality-Aware Projection-Out (CAPO) for distinguishing inter-NP CA maps and Adaptive Token Mixing (ATM) for enhancing inter-NP separation while maintaining intra-NP cohesion in CA maps. Extensive experiments confirm that TokeBi outperforms prior arts across diverse baselines and datasets.
Authors: Ilir Tahiraj, Jeremialie Swadiryus, Felix Fent, Markus Lienkamp
Abstract: The goal of extrinsic calibration is the alignment of sensor data to ensure an accurate representation of the surroundings and enable sensor fusion applications. From a safety perspective, sensor calibration is a key enabler of autonomous driving. In the current state of the art, a trend from target-based offline calibration towards targetless online calibration can be observed. However, online calibration is subject to strict real-time and resource constraints which are not met by state-of-the-art methods. This is mainly due to the high number of parameters to estimate, the reliance on geometric features, or the dependence on specific vehicle maneuvers. To meet these requirements and ensure the vehicle's safety at any time, we propose a miscalibration detection framework that shifts the focus from the direct regression of calibration parameters to a binary classification of the calibration state, i.e., calibrated or miscalibrated. Therefore, we propose a contrastive learning approach that compares embedded features in a latent space to classify the calibration state of two different sensor modalities. Moreover, we provide a comprehensive analysis of the feature embeddings and challenging calibration errors that highlight the performance of our approach. As a result, our method outperforms the current state-of-the-art in terms of detection performance, inference time, and resource demand. The code is open source and available on https://github.com/TUMFTM/MiscalibrationDetection.
Authors: Yi Peng, Peiyu Wang, Xiaokun Wang, Yichen Wei, Jiangbo Pei, Weijie Qiu, Ai Jian, Yunzhuo Hao, Jiachun Pan, Tianyidan Xie, Li Ge, Rongxian Zhuang, Xuchen Song, Yang Liu, Yahui Zhou
Abstract: We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility.
Authors: Ronghui Zhang, Yuhang Ma, Tengfei Li, Ziyu Lin, Yueying Wu, Junzhou Chen, Lin Zhang, Jia Hu, Tony Z. Qiu, Konghui Guo
Abstract: Lane detection is a critical component of Advanced Driver Assistance Systems (ADAS). Existing lane detection algorithms generally perform well under favorable weather conditions. However, their performance degrades significantly in adverse conditions, such as fog, which increases the risk of traffic accidents. This challenge is compounded by the lack of specialized datasets and methods designed for foggy environments. To address this, we introduce the FoggyLane dataset, captured in real-world foggy scenarios, and synthesize two additional datasets, FoggyCULane and FoggyTusimple, from existing popular lane detection datasets. Furthermore, we propose a robust Fog-Enhanced Network for lane detection, incorporating a Global Feature Fusion Module (GFFM) to capture global relationships in foggy images, a Kernel Feature Fusion Module (KFFM) to model the structural and positional relationships of lane instances, and a Low-level Edge Enhanced Module (LEEM) to address missing edge details in foggy conditions. Comprehensive experiments demonstrate that our method achieves state-of-the-art performance, with F1-scores of 95.04 on FoggyLane, 79.85 on FoggyCULane, and 96.95 on FoggyTusimple. Additionally, with TensorRT acceleration, the method reaches a processing speed of 38.4 FPS on the NVIDIA Jetson AGX Orin, confirming its real-time capabilities and robustness in foggy environments.
Authors: Hanxue Zhang, Haoran Jiang, Qingsong Yao, Yanan Sun, Renrui Zhang, Hao Zhao, Hongyang Li, Hongzi Zhu, Zetong Yang
Abstract: Despite the success of deep learning in close-set 3D object detection, existing approaches struggle with zero-shot generalization to novel objects and camera configurations. We introduce DetAny3D, a promptable 3D detection foundation model capable of detecting any novel object under arbitrary camera configurations using only monocular inputs. Training a foundation model for 3D detection is fundamentally constrained by the limited availability of annotated 3D data, which motivates DetAny3D to leverage the rich prior knowledge embedded in extensively pre-trained 2D foundation models to compensate for this scarcity. To effectively transfer 2D knowledge to 3D, DetAny3D incorporates two core modules: the 2D Aggregator, which aligns features from different 2D foundation models, and the 3D Interpreter with Zero-Embedding Mapping, which mitigates catastrophic forgetting in 2D-to-3D knowledge transfer. Experimental results validate the strong generalization of our DetAny3D, which not only achieves state-of-the-art performance on unseen categories and novel camera configurations, but also surpasses most competitors on in-domain data.DetAny3D sheds light on the potential of the 3D foundation model for diverse applications in real-world scenarios, e.g., rare object detection in autonomous driving, and demonstrates promise for further exploration of 3D-centric tasks in open-world settings. More visualization results can be found at DetAny3D project page.
Authors: Ali Haider, Muhammad Salman Ali, Maryam Qamar, Tahir Khalil, Soo Ye Kim, Jihyong Oh, Enzo Tartaglione, Sung-Ho Bae
Abstract: Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, their inherent formulation as a regression problem makes them prone to regression to the mean, limiting their ability to capture fine details, retain high-frequency information, and handle noise effectively. To address these challenges, we propose Iterative Implicit Neural Representations (I-INRs) a novel plug-and-play framework that enhances signal reconstruction through an iterative refinement process. I-INRs effectively recover high-frequency details, improve robustness to noise, and achieve superior reconstruction quality. Our framework seamlessly integrates with existing INR architectures, delivering substantial performance gains across various tasks. Extensive experiments show that I-INRs outperform baseline methods, including WIRE, SIREN, and Gauss, in diverse computer vision applications such as image restoration, image denoising, and object occupancy prediction.
Authors: Long Liu, Cihui Yang
Abstract: Table structure recognition is a key task in document analysis. However, the geometric deformation in deformed tables causes a weak correlation between content information and structure, resulting in downstream tasks not being able to obtain accurate content information. To obtain fine-grained spatial coordinates of cells, we propose the OG-HFYOLO model, which enhances the edge response by Gradient Orientation-aware Extractor, combines a Heterogeneous Kernel Cross Fusion module and a scale-aware loss function to adapt to multi-scale objective features, and introduces mask-driven non-maximal suppression in the post-processing, which replaces the traditional bounding box suppression mechanism. Furthermore, we also propose a data generator, filling the gap in the dataset for fine-grained deformation table cell spatial coordinate localization, and derive a large-scale dataset named Deformation Wired Table (DWTAL). Experiments show that our proposed model demonstrates excellent segmentation accuracy on all mainstream instance segmentation models. The dataset and the source code are open source: https://github.com/justliulong/OGHFYOLO.
Authors: Gaozheng Pei, Ke Ma, Yingfei Sun, Qianqian Xu, Qingming Huang
Abstract: The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of distribution information about adversarial perturbations in the pixel domain, it is often unavoidable to damage normal semantics. We turn to the frequency domain perspective, decomposing the image into amplitude spectrum and phase spectrum. We find that for both spectra, the damage caused by adversarial perturbations tends to increase monotonically with frequency. This means that we can extract the content and structural information of the original clean sample from the frequency components that are less damaged. Meanwhile, theoretical analysis indicates that existing purification methods indiscriminately damage all frequency components, leading to excessive damage to the image. Therefore, we propose a purification method that can eliminate adversarial perturbations while maximizing the preservation of the content and structure of the original image. Specifically, at each time step during the reverse process, for the amplitude spectrum, we replace the low-frequency components of the estimated image's amplitude spectrum with the corresponding parts of the adversarial image. For the phase spectrum, we project the phase of the estimated image into a designated range of the adversarial image's phase spectrum, focusing on the low frequencies. Empirical evidence from extensive experiments demonstrates that our method significantly outperforms most current defense methods.
Authors: Yuto Nakamura, Satoshi Kodera, Haruki Settai, Hiroki Shinohara, Masatsugu Tamura, Tomohiro Noguchi, Tatsuki Furusawa, Ryo Takizawa, Tempei Kabayama, Norihiko Takeda
Abstract: Coronary angiography (CAG) is the gold-standard imaging modality for evaluating coronary artery disease, but its interpretation and subsequent treatment planning rely heavily on expert cardiologists. To enable AI-based decision support, we introduce a two-stage, physician-curated pipeline and a bilingual (Japanese/English) CAG image-report dataset. First, we sample 14,686 frames from 539 exams and annotate them for key-frame detection and left/right laterality; a ConvNeXt-Base CNN trained on this data achieves 0.96 F1 on laterality classification, even on low-contrast frames. Second, we apply the CNN to 243 independent exams, extract 1,114 key frames, and pair each with its pre-procedure report and expert-validated diagnostic and treatment summary, yielding a parallel corpus. We then fine-tune three open-source VLMs (PaliGemma2, Gemma3, and ConceptCLIP-enhanced Gemma3) via LoRA and evaluate them using VLScore and cardiologist review. Although PaliGemma2 w/LoRA attains the highest VLScore, Gemma3 w/LoRA achieves the top clinician rating (mean 7.20/10); we designate this best-performing model as CAG-VLM. These results demonstrate that specialized, fine-tuned VLMs can effectively assist cardiologists in generating clinical reports and treatment recommendations from CAG images.
Authors: Xiaokun Wang, Peiyu Wang, Jiangbo Pei, Wei Shen, Yi Peng, Yunzhuo Hao, Weijie Qiu, Ai Jian, Tianyidan Xie, Xuchen Song, Yang Liu, Yahui Zhou
Abstract: We propose Skywork-VL Reward, a multimodal reward model that provides reward signals for both multimodal understanding and reasoning tasks. Our technical approach comprises two key components: First, we construct a large-scale multimodal preference dataset that covers a wide range of tasks and scenarios, with responses collected from both standard vision-language models (VLMs) and advanced VLM reasoners. Second, we design a reward model architecture based on Qwen2.5-VL-7B-Instruct, integrating a reward head and applying multi-stage fine-tuning using pairwise ranking loss on pairwise preference data. Experimental evaluations show that Skywork-VL Reward achieves state-of-the-art results on multimodal VL-RewardBench and exhibits competitive performance on the text-only RewardBench benchmark. Furthermore, preference data constructed based on our Skywork-VL Reward proves highly effective for training Mixed Preference Optimization (MPO), leading to significant improvements in multimodal reasoning capabilities. Our results underscore Skywork-VL Reward as a significant advancement toward general-purpose, reliable reward models for multimodal alignment. Our model has been publicly released to promote transparency and reproducibility.
Authors: Zifan Wang, Jingwei Li, Yitang Li, Yunze Liu
Abstract: This paper introduces MutualNeRF, a framework enhancing Neural Radiance Field (NeRF) performance under limited samples using Mutual Information Theory. While NeRF excels in 3D scene synthesis, challenges arise with limited data and existing methods that aim to introduce prior knowledge lack theoretical support in a unified framework. We introduce a simple but theoretically robust concept, Mutual Information, as a metric to uniformly measure the correlation between images, considering both macro (semantic) and micro (pixel) levels. For sparse view sampling, we strategically select additional viewpoints containing more non-overlapping scene information by minimizing mutual information without knowing ground truth images beforehand. Our framework employs a greedy algorithm, offering a near-optimal solution. For few-shot view synthesis, we maximize the mutual information between inferred images and ground truth, expecting inferred images to gain more relevant information from known images. This is achieved by incorporating efficient, plug-and-play regularization terms. Experiments under limited samples show consistent improvement over state-of-the-art baselines in different settings, affirming the efficacy of our framework.
Authors: Yibo Gao, Hangqi Zhou, Zheyao Gao, Bomin Wang, Shangqi Gao, Sihan Wang, Xiahai Zhuang
Abstract: The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these limitations, we propose Concept Rule Learner (CRL), a novel framework to learn Boolean logical rules from binarized visual concepts. CRL employs logical layers to capture concept correlations and extract clinically meaningful rules, thereby providing both local and global interpretability. Experiments on two medical image classification tasks show that CRL achieves competitive performance with existing methods while significantly improving generalizability to out-of-distribution data. The code of our work is available at https://github.com/obiyoag/crl.
Authors: Xiaoran Yin, Xu Luo, Hao Wu, Lianli Gao, Jingkuan Song
Abstract: The automatic control of mobile devices is essential for efficiently performing complex tasks that involve multiple sequential steps. However, these tasks pose significant challenges due to the limited environmental information available at each step, primarily through visual observations. As a result, current approaches, which typically rely on reactive policies, focus solely on immediate observations and often lead to suboptimal decision-making. To address this problem, we propose \textbf{Foresighted Planning with World Model-Driven Code Execution (FPWC)},a framework that prioritizes natural language understanding and structured reasoning to enhance the agent's global understanding of the environment by developing a task-oriented, refinable \emph{world model} at the outset of the task. Foresighted actions are subsequently generated through iterative planning within this world model, executed in the form of executable code. Extensive experiments conducted in simulated environments and on real mobile devices demonstrate that our method outperforms previous approaches, particularly achieving a 44.4\% relative improvement in task success rate compared to the state-of-the-art in the simulated environment. Code and demo are provided in the supplementary material.
Authors: Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zelin Peng, Zhiwei Yang, Jionglong Su, Minquan Lin, Yifan Peng, Xuelian Cheng, Imran Razzak, Zongyuan Ge
Abstract: Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in the decoding strategy, we propose to leverage causal masks to establish information propagation between multimodal tokens. The hypothesis is that insufficient interaction between those tokens may lead the model to rely on outlier tokens, overlooking dense and rich contextual cues. Therefore, we propose to intervene in the propagation process by tackling outlier tokens to enhance in-context inference. With this goal, we present FarSight, a versatile plug-and-play decoding strategy to reduce attention interference from outlier tokens merely by optimizing the causal mask. The heart of our method is effective token propagation. We design an attention register structure within the upper triangular matrix of the causal mask, dynamically allocating attention to capture attention diverted to outlier tokens. Moreover, a positional awareness encoding method with a diminishing masking rate is proposed, allowing the model to attend to further preceding tokens, especially for video sequence tasks. With extensive experiments, FarSight demonstrates significant hallucination-mitigating performance across different MLLMs on both image and video benchmarks, proving its effectiveness.
Authors: Jun Xie, Xiongjun Guan, Yingjian Zhu, Zhaoran Zhao, Xinming Wang, Hongzhu Yi, Feng Chen, Zhepeng Wang
Abstract: In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and adapt them to video understanding tasks via few-shot learning and model ensemble strategies. Specifically, diversified prompt styles and process paradigms are systematically explored and evaluated to effectively guide the attention of large models, fully unleashing their powerful generalization and adaptability abilities. Experimental results demonstrate that, with our carefully designed approach, directly utilizing an individual multimodal model already outperforms the previous state-of-the-art (SOTA) method which includes several additional processes. Besides, an additional stage is further introduced that facilitates the cooperation and ensemble of periodic results, which achieves impressive performance improvements. We hope this work serves as a valuable reference for the practical application of large models and inspires future research in the field. Our Code is available at https://github.com/XiongjunGuan/EgoSchema-CVPR25.
Authors: Junze Wang, Lei Fan, Weipeng Jing, Donglin Di, Yang Song, Sidong Liu, Cong Cong
Abstract: Existing methods for multimodal MRI segmentation with missing modalities typically assume that all MRI modalities are available during training. However, in clinical practice, some modalities may be missing due to the sequential nature of MRI acquisition, leading to performance degradation. Furthermore, retraining models to accommodate newly available modalities can be inefficient and may cause overfitting, potentially compromising previously learned knowledge. To address these challenges, we propose Replay-based Hypergraph Domain Incremental Learning (ReHyDIL) for brain tumor segmentation with missing modalities. ReHyDIL leverages Domain Incremental Learning (DIL) to enable the segmentation model to learn from newly acquired MRI modalities without forgetting previously learned information. To enhance segmentation performance across diverse patient scenarios, we introduce the Cross-Patient Hypergraph Segmentation Network (CHSNet), which utilizes hypergraphs to capture high-order associations between patients. Additionally, we incorporate Tversky-Aware Contrastive (TAC) loss to effectively mitigate information imbalance both across and within different modalities. Extensive experiments on the BraTS2019 dataset demonstrate that ReHyDIL outperforms state-of-the-art methods, achieving an improvement of over 2% in the Dice Similarity Coefficient across various tumor regions. Our code is available at https://github.com/reeive/ReHyDIL.
Authors: Tanqiu Jiang, Jiacheng Liang, Rongyi Zhu, Jiawei Zhou, Fenglong Ma, Ting Wang
Abstract: Large vision-language models (VLMs) are highly vulnerable to jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates multimodal jailbreak attacks through optimizing the model's key-value (KV) caches. Rather than relying on curated safety-specific data or costly image-to-text conversion, we introduce a new formulation of the safety-relevant distributional shift induced by the visual modality. This formulation enables DTR to dynamically adjust visual token weights, minimizing the impact of adversarial visual inputs while preserving the model's general capabilities and inference efficiency. Extensive evaluation across diverse VLMs and attack benchmarks demonstrates that \sys outperforms existing defenses in both attack robustness and benign task performance, marking the first successful application of KV cache optimization for safety enhancement in multimodal foundation models. (warning: this paper contains potentially harmful content generated by VLMs.)
Authors: Dingqing Ye, Chao Fan, Zhanbo Huang, Chengwen Luo, Jianqiang Li, Shiqi Yu, Xiaoming Liu
Abstract: Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR\_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code will be publicly available.
Authors: Zhen Li, Duan Li, Yukai Guo, Xinyuan Guo, Bowen Li, Lanxi Xiao, Shenyu Qiao, Jiashu Chen, Zijian Wu, Hui Zhang, Xinhuan Shu, Shixia Liu
Abstract: Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 330 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.
Authors: Sicheng Feng, Song Wang, Shuyi Ouyang, Lingdong Kong, Zikai Song, Jianke Zhu, Huan Wang, Xinchao Wang
Abstract: Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding and spatial reasoning abilities of MLLMs. ReasonMap encompasses high-resolution transit maps from 30 cities across 13 countries and includes 1,008 question-answer pairs spanning two question types and three templates. Furthermore, we design a two-level evaluation pipeline that properly assesses answer correctness and quality. Comprehensive evaluations of 15 popular MLLMs, including both base and reasoning variants, reveal a counterintuitive pattern: among open-source models, base models outperform reasoning ones, while the opposite trend is observed in closed-source models. Additionally, performance generally degrades when visual inputs are masked, indicating that while MLLMs can leverage prior knowledge to answer some questions, fine-grained visual reasoning tasks still require genuine visual perception for strong performance. Our benchmark study offers new insights into visual reasoning and contributes to investigating the gap between open-source and closed-source models.
Authors: Chun Wang, Xiaoran Pan, Zihao Pan, Haofan Wang, Yiren Song
Abstract: Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images and their integration with external world knowledge for systematic reasoning. Current approaches to geo-localization tasks often lack robust reasoning mechanisms and explainability, limiting their effectiveness. To address these limitations, we propose the Geo Reason Enhancement (GRE) Suite, a novel framework that augments VLMs with structured reasoning chains for accurate and interpretable location inference. The GRE Suite is systematically developed across three key dimensions: dataset, model, and benchmark. First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis. Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision. Finally, we construct the Geo Reason Evaluation Benchmark (GREval-Bench), a comprehensive evaluation framework that assesses VLMs across diverse urban, natural, and landmark scenes to measure both coarse-grained (e.g., country, continent) and fine-grained (e.g., city, street) localization performance. Experimental results demonstrate that GRE significantly outperforms existing methods across all granularities of geo-localization tasks, underscoring the efficacy of reasoning-augmented VLMs in complex geographic inference. Code and data will be released at https://github.com/Thorin215/GRE.
Authors: Yaping He, Jianfeng Cai, Qicong Hu, Peiqing Wang
Abstract: To address the challenges posed by the large number of parameters in existing remote sensing image classification models, which hinder deployment on resource-constrained devices, this paper proposes a lightweight classification method based on knowledge distillation. Specifically, G-GhostNet is adopted as the backbone network, leveraging feature reuse to reduce redundant parameters and significantly improve inference efficiency. In addition, a decoupled knowledge distillation strategy is employed, which separates target and non-target classes to effectively enhance classification accuracy. Experimental results on the RSOD and AID datasets demonstrate that, compared with the high-parameter VGG-16 model, the proposed method achieves nearly equivalent Top-1 accuracy while reducing the number of parameters by 6.24 times. This approach strikes an excellent balance between model size and classification performance, offering an efficient solution for deployment on resource-limited devices.
Authors: Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, Victoria W., Fuzheng Zhang
Abstract: Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooking the holistic nature of video content. To address this, we introduce TUNA, a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos, with two complementary tasks: captioning and QA. Our TUNA features diverse video scenarios and dynamics, assisted by interpretable and robust evaluation criteria. We evaluate several leading models on our benchmark, providing fine-grained performance assessments across various dimensions. This evaluation reveals key challenges in video temporal understanding, such as limited action description, inadequate multi-subject understanding, and insensitivity to camera motion, offering valuable insights for improving video understanding models. The data and code are available at https://friedrichor.github.io/projects/TUNA.
Authors: Aiyue Chen, Bin Dong, Jingru Li, Jing Lin, Kun Tian, Yiwu Yao, Gongyi Wang
Abstract: Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion}, a novel training-free sparse attention method that exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality. Specifically, we identify three unique sparse patterns in video generation attention calculations--Spatial Pattern, Temporal Pattern and Textural Pattern. The sparse pattern for each attention head is determined online with negligible overhead (\textasciitilde\,0.2\%) with our proposed {\bf ARM} (Adaptive Recognition Module) during inference. Our proposed {\bf RainFusion} is a plug-and-play method, that can be seamlessly integrated into state-of-the-art 3D-attention video generation models without additional training or calibration. We evaluate our method on leading open-sourced models including HunyuanVideo, OpenSoraPlan-1.2 and CogVideoX-5B, demonstrating its broad applicability and effectiveness. Experimental results show that RainFusion achieves over {\bf 2\(\times\)} speedup in attention computation while maintaining video quality, with only a minimal impact on VBench scores (-0.2\%).
Authors: Pardis Taghavi, Tian Liu, Renjie Li, Reza Langari, Zhengzhong Tu
Abstract: Instance segmentation demands costly per-pixel annotations and large models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into compact experts using limited labeled and abundant unlabeled data. CAST unfolds in three stages: (1) domain adaptation of the VFM teacher(s) via self-training with contrastive pixel calibration, (2) distillation into a compact student via a unified multi-objective loss that couples standard supervision and pseudo-labels with our instance-aware pixel-wise contrastive term, and (3) fine-tuning on labeled data to remove residual pseudo-label bias. Central to CAST is an \emph{instance-aware pixel-wise contrastive loss} that fuses mask and class scores to mine informative negatives and enforce clear inter-instance margins. By maintaining this contrastive signal across both adaptation and distillation, we align teacher and student embeddings and fully leverage unlabeled images. On Cityscapes and ADE20K, our ~11X smaller student surpasses its adapted VFM teacher(s) by +3.4 AP (33.9 vs. 30.5) and +1.5 AP (16.7 vs. 15.2) and outperforms state-of-the-art semi-supervised approaches.
Authors: Minchul Kim, Anil Jain, Xiaoming Liu
Abstract: Over the past 50 years, automated face recognition has evolved from rudimentary, handcrafted systems into sophisticated deep learning models that rival and often surpass human performance. This paper chronicles the history and technological progression of FR, from early geometric and statistical methods to modern deep neural architectures leveraging massive real and AI-generated datasets. We examine key innovations that have shaped the field, including developments in dataset, loss function, neural network design and feature fusion. We also analyze how the scale and diversity of training data influence model generalization, drawing connections between dataset growth and benchmark improvements. Recent advances have achieved remarkable milestones: state-of-the-art face verification systems now report False Negative Identification Rates of 0.13% against a 12.4 million gallery in NIST FRVT evaluations for 1:N visa-to-border matching. While recent advances have enabled remarkable accuracy in high- and low-quality face scenarios, numerous challenges persist. While remarkable progress has been achieved, several open research problems remain. We outline critical challenges and promising directions for future face recognition research, including scalability, multi-modal fusion, synthetic identity generation, and explainable systems.
Authors: Jisheng Dang, Jingze Wu, Teng Wang, Xuanhui Lin, Nannan Zhu, Hongbo Chen, Wei-Shi Zheng, Meng Wang, Tat-Seng Chua
Abstract: Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations persist: 1) they often produce unfocused, verbose reasoning chains that obscure salient spatiotemporal cues and 2) binary rewarding fails to account for partially correct answers, resulting in high reward variance and inefficient learning. In this paper, we propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity. Specifically, we employs a token weighting mechanism that prioritizes tokens with high informational density (estimated by intra-group information entropy), suppressing redundant tokens like generic reasoning prefixes. Furthermore, we reformulate RL training by shifting from single-choice to multi-choice QA tasks, where soft rewards enable finer-grained gradient estimation by distinguishing partial correctness. Additionally, we propose question-answer inversion, a data augmentation strategy to generate diverse multi-choice samples from existing benchmarks. Experiments demonstrate state-of-the-art performance on several video reasoning and general understanding benchmarks. Notably, TW-GRPO achieves 50.4\% accuracy on CLEVRER (18.8\% improvement over Video-R1) and 65.8\% on MMVU. Our codes are available at \href{https://github.com/longmalongma/TW-GRPO}.
Authors: Adrian Azzarelli, Ge Gao, Ho Man Kwan, Fan Zhang, Nantheera Anantrasirichai, Ollie Moolan-Feroze, David Bull
Abstract: As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing volumetric video datasets lack diverse content in terms of both semantic and low-level features that are commonly present in real-world production pipelines. In this context, we propose a new dataset, ViVo, for VolumetrIc VideO reconstruction and compression. The dataset is faithful to real-world volumetric video production and is the first dataset to extend the definition of diversity to include both human-centric characteristics (skin, hair, etc.) and dynamic visual phenomena (transparent, reflective, liquid, etc.). Each video sequence in this database contains raw data including fourteen multi-view RGB and depth video pairs, synchronized at 30FPS with per-frame calibration and audio data, and their associated 2-D foreground masks and 3-D point clouds. To demonstrate the use of this database, we have benchmarked three state-of-the-art (SotA) 3-D reconstruction methods and two volumetric video compression algorithms. The obtained results evidence the challenging nature of the proposed dataset and the limitations of existing datasets for both volumetric video reconstruction and compression tasks, highlighting the need to develop more effective algorithms for these applications. The database and the associated results are available at https://vivo-bvicr.github.io/
Authors: Zhan Li, Mingyu Zhao, Xin Dong, Haibin Ling, Bingyao Huang
Abstract: Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of more robust classifiers. However, existing approaches primarily focus on individual classifiers and fixed camera poses, often neglecting the complexities of multi-classifier systems and scenarios with varying camera poses. This limitation reduces their effectiveness when introducing new classifiers or camera poses. In this paper, we introduce Classifier-Agnostic Projector-Based Adversarial Attack (CAPAA) to address these issues. First, we develop a novel classifier-agnostic adversarial loss and optimization framework that aggregates adversarial and stealthiness loss gradients from multiple classifiers. Then, we propose an attention-based gradient weighting mechanism that concentrates perturbations on regions of high classification activation, thereby improving the robustness of adversarial projections when applied to scenes with varying camera poses. Our extensive experimental evaluations demonstrate that CAPAA achieves both a higher attack success rate and greater stealthiness compared to existing baselines. Codes are available at: https://github.com/ZhanLiQxQ/CAPAA.
Authors: Wenyan Cong, Yiqing Liang, Yancheng Zhang, Ziyi Yang, Yan Wang, Boris Ivanovic, Marco Pavone, Chen Chen, Zhangyang Wang, Zhiwen Fan
Abstract: Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emerged, directly predicting dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters. Since late 2023, the field has exploded with diverse variants, but systematic evaluation is lacking. In this work, we present the first comprehensive benchmark for 3D GFMs, covering five core tasks: sparse-view depth estimation, video depth estimation, 3D reconstruction, multi-view pose estimation, novel view synthesis, and spanning both standard and challenging out-of-distribution datasets. Our standardized toolkit automates dataset handling, evaluation protocols, and metric computation to ensure fair, reproducible comparisons. We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains, and derive key insights to guide future model scaling and optimization. All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.
Authors: Rachid Zeghlache, Ikram Brahim, Pierre-Henri Conze, Mathieu Lamard, Mohammed El Amine Lazouni, Zineb Aziza Elaouaber, Leila Ryma Lazouni, Christopher Nielsen, Ahmad O. Ahsan, Matthias Wilms, Nils D. Forkert, Lovre Antonio Budimir, Ivana Matovinovi\'c, Donik Vr\v{s}nak, Sven Lon\v{c}ari\'c, Philippe Zhang, Weili Jiang, Yihao Li, Yiding Hao, Markus Frohmann, Patrick Binder, Marcel Huber, Taha Emre, Teresa Finisterra Ara\'ujo, Marzieh Oghbaie, Hrvoje Bogunovi\'c, Amerens A. Bekkers, Nina M. van Liebergen, Hugo J. Kuijf, Abdul Qayyum, Moona Mazher, Steven A. Niederer, Alberto J. Beltr\'an-Carrero, Juan J. G\'omez-Valverde, Javier Torresano-Rodr\'iquez, \'Alvaro Caballero-Sastre, Mar\'ia J. Ledesma Carbayo, Yosuke Yamagishi, Yi Ding, Robin Peretzke, Alexandra Ertl, Maximilian Fischer, Jessica K\"achele, Sofiane Zehar, Karim Boukli Hacene, Thomas Monfort, B\'eatrice Cochener, Mostafa El Habib Daho, Anas-Alexis Benyoussef, Gwenol\'e Quellec
Abstract: The MARIO challenge, held at MICCAI 2024, focused on advancing the automated detection and monitoring of age-related macular degeneration (AMD) through the analysis of optical coherence tomography (OCT) images. Designed to evaluate algorithmic performance in detecting neovascular activity changes within AMD, the challenge incorporated unique multi-modal datasets. The primary dataset, sourced from Brest, France, was used by participating teams to train and test their models. The final ranking was determined based on performance on this dataset. An auxiliary dataset from Algeria was used post-challenge to evaluate population and device shifts from submitted solutions. Two tasks were involved in the MARIO challenge. The first one was the classification of evolution between two consecutive 2D OCT B-scans. The second one was the prediction of future AMD evolution over three months for patients undergoing anti-vascular endothelial growth factor (VEGF) therapy. Thirty-five teams participated, with the top 12 finalists presenting their methods. This paper outlines the challenge's structure, tasks, data characteristics, and winning methodologies, setting a benchmark for AMD monitoring using OCT, infrared imaging, and clinical data (such as the number of visits, age, gender, etc.). The results of this challenge indicate that artificial intelligence (AI) performs as well as a physician in measuring AMD progression (Task 1) but is not yet able of predicting future evolution (Task 2).
Authors: Huy Le, Nhat Chung, Tung Kieu, Anh Nguyen, Ngan Le
Abstract: Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to mitigate biases in both visual and textual representations. Our approach begins by generating scene elements that characterize each video by identifying relevant entities/objects and activities. For visual debiasing, we integrate these scene elements into the video embeddings, enhancing them to emphasize fine-grained and salient details. For textual debiasing, we introduce a mechanism to disentangle text features into content and bias components, enabling the model to focus on meaningful content while separately handling biased information. Extensive experiments and ablation studies across five major TVR benchmarks (i.e., MSR-VTT, MSVD, LSMDC, ActivityNet, and DiDeMo) demonstrate the competitive performance of BiMa. Additionally, the model's bias mitigation capability is consistently validated by its strong results on out-of-distribution retrieval tasks.
Authors: Hicham Eddoubi, Jonas Ricker, Federico Cocchi, Lorenzo Baraldi, Angelo Sotgiu, Maura Pintor, Marcella Cornia, Lorenzo Baraldi, Asja Fischer, Rita Cucchiara, Battista Biggio
Abstract: AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinformation, the detection of AI-generated images is a pressing challenge and an active research topic. While many of the presented methods claim to achieve high detection accuracy, they are usually evaluated under idealized conditions. In particular, the adversarial robustness is often neglected, potentially due to a lack of awareness or the substantial effort required to conduct a comprehensive robustness analysis. In this work, we tackle this problem by providing a simpler means to assess the robustness of AI-generated image detectors. We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples. The dataset is created by running attacks against an ensemble of seven state-of-the-art detectors and images generated by four different text-to-image models. Extensive experiments show that our methodology generates adversarial images that transfer with a high success rate to unseen detectors, which can be used to quickly provide an approximate yet still reliable estimate of a detector's adversarial robustness. Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples, highlighting the critical need for the development of more robust methods. We release our dataset at https://huggingface.co/datasets/aimagelab/RAID and evaluation code at https://github.com/pralab/RAID.
URLs: https://huggingface.co/datasets/aimagelab/RAID, https://github.com/pralab/RAID.
Authors: Takayuki Komatsu, Yoshiyuki Ohmura, Kayato Nishitsunoi, Yasuo Kuniyoshi
Abstract: The main goal of representation learning is to acquire meaningful representations from real-world sensory inputs without supervision. Representation learning explains some aspects of human development. Various neural network (NN) models have been proposed that acquire empirically good representations. However, the formulation of a good representation has not been established. We recently proposed a method for categorizing changes between a pair of sensory inputs. A unique feature of this approach is that transformations between two sensory inputs are learned to satisfy algebraic structural constraints. Conventional representation learning often assumes that disentangled independent feature axes is a good representation; however, we found that such a representation cannot account for conditional independence. To overcome this problem, we proposed a new method using group decomposition in Galois algebra theory. Although this method is promising for defining a more general representation, it assumes pixel-to-pixel translation without feature extraction, and can only process low-resolution images with no background, which prevents real-world application. In this study, we provide a simple method to apply our group decomposition theory to a more realistic scenario by combining feature extraction and object segmentation. We replace pixel translation with feature translation and formulate object segmentation as grouping features under the same transformation. We validated the proposed method on a practical dataset containing both real-world object and background. We believe that our model will lead to a better understanding of human development of object recognition in the real world.
Authors: Fuyi Zhang, Zhu Yu, Chunhao Li, Runmin Zhang, Xiaokai Bai, Zili Zhou, Si-Yuan Cao, Fang Wang, Hui-Liang Shen
Abstract: Monocular depth estimation aims to determine the depth of each pixel from an RGB image captured by a monocular camera. The development of deep learning has significantly advanced this field by facilitating the learning of depth features from some well-annotated datasets \cite{Geiger_Lenz_Stiller_Urtasun_2013,silberman2012indoor}. Eigen \textit{et al.} \cite{eigen2014depth} first introduce a multi-scale fusion network for depth regression. Following this, subsequent improvements have come from reinterpreting the regression task as a classification problem \cite{bhat2021adabins,Li_Wang_Liu_Jiang_2022}, incorporating additional priors \cite{shao2023nddepth,yang2023gedepth}, and developing more effective objective function \cite{xian2020structure,Yin_Liu_Shen_Yan_2019}. Despite these advances, generalizing to unseen domains remains a challenge. Recently, several methods have employed affine-invariant loss to enable multi-dataset joint training \cite{MiDaS,ZeroDepth,guizilini2023towards,Dany}. Among them, Depth Anything \cite{Dany} has shown leading performance in zero-shot monocular depth estimation. While it struggles to estimate accurate metric depth due to the lack of explicit depth cues, it excels at extracting structural information from unseen images, producing structure-detailed monocular depth.
Authors: Haosong Liu, Yuge Cheng, Zihan Liu, Aiyue Chen, Jing Lin, Yiwu Yao, Chen Chen, Jingwen Leng, Yu Feng, Minyi Guo
Abstract: Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment. While existing acceleration methods reduce workload at various granularities, they often rely on heuristics, limiting their applicability. We introduce ASTRAEA, an automatic framework that searches for near-optimal configurations for vDiT-based video generation. At its core, ASTRAEA proposes a lightweight token selection mechanism and a memory-efficient, GPU-parallel sparse attention strategy, enabling linear reductions in execution time with minimal impact on generation quality. To determine optimal token reduction for different timesteps, we further design a search framework that leverages a classic evolutionary algorithm to automatically determine the distribution of the token budget effectively. Together, ASTRAEA achieves up to 2.4x inference speedup on a single GPU with great scalability (up to 13.2x speedup on 8 GPUs) while retaining better video quality compared to the state-of-the-art methods (<0.5% loss on the VBench score compared to the baseline vDiT models).
Authors: Daniel Rho, Jun Myeong Choi, Biswadip Dey, Roni Sengupta
Abstract: Neural rendering has made significant strides in 3D reconstruction and novel view synthesis. With the integration with physics, it opens up new applications. The inverse problem of estimating physics from visual data, however, still remains challenging, limiting its effectiveness for applications like physically accurate digital twin creation in robotics and XR. Existing methods that incorporate physics into neural rendering frameworks typically require dense multi-view videos as input, making them impractical for scalable, real-world use. When presented with sparse multi-view videos, the sequential optimization strategy used by existing approaches introduces significant error accumulation, e.g., poor initial 3D reconstruction leads to bad material parameter estimation in subsequent stages. Instead of sequential optimization, directly optimizing all parameters at the same time also fails due to the highly non-convex and often non-differentiable nature of the problem. We propose ProJo4D, a progressive joint optimization framework that gradually increases the set of jointly optimized parameters guided by their sensitivity, leading to fully joint optimization over geometry, appearance, physical state, and material property. Evaluations on PAC-NeRF and Spring-Gaus datasets show that ProJo4D outperforms prior work in 4D future state prediction, novel view rendering of future state, and material parameter estimation, demonstrating its effectiveness in physically grounded 4D scene understanding. For demos, please visit the project webpage: https://daniel03c1.github.io/ProJo4D/
Authors: Markiian Mandzak, Elvira Yang, Anna Zapaishchykova, Yu-Hui Chen, Lucas Heilbroner, John Zielke, Divyanshu Tak, Reza Mojahed-Yazdi, Francesca Romana Mussa, Zezhong Ye, Sridhar Vajapeyam, Viviana Benitez, Ralph Salloum, Susan N. Chi, Houman Sotoudeh, Jakob Seidlitz, Sabine Mueller, Hugo J. W. L. Aerts, Tina Y. Poussaint, Benjamin H. Kann
Abstract: Extracranial tissues visible on brain magnetic resonance imaging (MRI) may hold significant value for characterizing health conditions and clinical decision-making, yet they are rarely quantified. Current tools have not been widely validated, particularly in settings of developing brains or underlying pathology. We present TissUnet, a deep learning model that segments skull bone, subcutaneous fat, and muscle from routine three-dimensional T1-weighted MRI, with or without contrast enhancement. The model was trained on 155 paired MRI-computed tomography (CT) scans and validated across nine datasets covering a wide age range and including individuals with brain tumors. In comparison to AI-CT-derived labels from 37 MRI-CT pairs, TissUnet achieved a median Dice coefficient of 0.79 [IQR: 0.77-0.81] in a healthy adult cohort. In a second validation using expert manual annotations, median Dice was 0.83 [IQR: 0.83-0.84] in healthy individuals and 0.81 [IQR: 0.78-0.83] in tumor cases, outperforming previous state-of-the-art method. Acceptability testing resulted in an 89% acceptance rate after adjudication by a tie-breaker(N=108 MRIs), and TissUnet demonstrated excellent performance in the blinded comparative review (N=45 MRIs), including both healthy and tumor cases in pediatric populations. TissUnet enables fast, accurate, and reproducible segmentation of extracranial tissues, supporting large-scale studies on craniofacial morphology, treatment effects, and cardiometabolic risk using standard brain T1w MRI.
Authors: Wenyuan Li, Shunlin Liang, Yuxiang Zhang, Liqin Liu, Keyan Chen, Yongzhe Chen, Han Ma, Jianglei Xu, Yichuan Ma, Shikang Guan, Zhenwei Shi
Abstract: Fine-grained crop type classification serves as the fundamental basis for large-scale crop mapping and plays a vital role in ensuring food security. It requires simultaneous capture of both phenological dynamics (obtained from multi-temporal satellite data like Sentinel-2) and subtle spectral variations (demanding nanometer-scale spectral resolution from hyperspectral imagery). Research combining these two modalities remains scarce currently due to challenges in hyperspectral data acquisition and crop types annotation costs. To address these issues, we construct a hierarchical hyperspectral crop dataset (H2Crop) by integrating 30m-resolution EnMAP hyperspectral data with Sentinel-2 time series. With over one million annotated field parcels organized in a four-tier crop taxonomy, H2Crop establishes a vital benchmark for fine-grained agricultural crop classification and hyperspectral image processing. We propose a dual-stream Transformer architecture that synergistically processes these modalities. It coordinates two specialized pathways: a spectral-spatial Transformer extracts fine-grained signatures from hyperspectral EnMAP data, while a temporal Swin Transformer extracts crop growth patterns from Sentinel-2 time series. The designed hierarchical classification head with hierarchical fusion then simultaneously delivers multi-level crop type classification across all taxonomic tiers. Experiments demonstrate that adding hyperspectral EnMAP data to Sentinel-2 time series yields a 4.2% average F1-scores improvement (peaking at 6.3%). Extensive comparisons also confirm our method's higher accuracy over existing deep learning approaches for crop type classification and the consistent benefits of hyperspectral data across varying temporal windows and crop change scenarios. Codes and dataset are available at https://github.com/flyakon/H2Crop.
Authors: Md. Alamin Talukder, Md. Manowarul Islam, Md Ashraf Uddin
Abstract: Brain tumors present a grave risk to human life, demanding precise and timely diagnosis for effective treatment. Inaccurate identification of brain tumors can significantly diminish life expectancy, underscoring the critical need for precise diagnostic methods. Manual identification of brain tumors within vast Magnetic Resonance Imaging (MRI) image datasets is arduous and time-consuming. Thus, the development of a reliable deep learning (DL) model is essential to enhance diagnostic accuracy and ultimately save lives. This study introduces an innovative optimization-based deep ensemble approach employing transfer learning (TL) to efficiently classify brain tumors. Our methodology includes meticulous preprocessing, reconstruction of TL architectures, fine-tuning, and ensemble DL models utilizing weighted optimization techniques such as Genetic Algorithm-based Weight Optimization (GAWO) and Grid Search-based Weight Optimization (GSWO). Experimentation is conducted on the Figshare Contrast-Enhanced MRI (CE-MRI) brain tumor dataset, comprising 3064 images. Our approach achieves notable accuracy scores, with Xception, ResNet50V2, ResNet152V2, InceptionResNetV2, GAWO, and GSWO attaining 99.42%, 98.37%, 98.22%, 98.26%, 99.71%, and 99.76% accuracy, respectively. Notably, GSWO demonstrates superior accuracy, averaging 99.76\% accuracy across five folds on the Figshare CE-MRI brain tumor dataset. The comparative analysis highlights the significant performance enhancement of our proposed model over existing counterparts. In conclusion, our optimized deep ensemble model exhibits exceptional accuracy in swiftly classifying brain tumors. Furthermore, it has the potential to assist neurologists and clinicians in making accurate and immediate diagnostic decisions.
Authors: Tianyuan Wang, Felix Lucka, Tristan van Leeuwen
Abstract: In X-ray Computed Tomography (CT), projections from many angles are acquired and used for 3D reconstruction. To make CT suitable for in-line quality control, reducing the number of angles while maintaining reconstruction quality is necessary. Sparse-angle tomography is a popular approach for obtaining 3D reconstructions from limited data. To optimize its performance, one can adapt scan angles sequentially to select the most informative angles for each scanned object. Mathematically, this corresponds to solving an optimal experimental design (OED) problem. OED problems are high-dimensional, non-convex, bi-level optimization problems that cannot be solved online, i.e., during the scan. To address these challenges, we pose the OED problem as a partially observable Markov decision process in a Bayesian framework, and solve it through deep reinforcement learning. The approach learns efficient non-greedy policies to solve a given class of OED problems through extensive offline training rather than solving a given OED problem directly via numerical optimization. As such, the trained policy can successfully find the most informative scan angles online. We use a policy training method based on the Actor-Critic approach and evaluate its performance on 2D tomography with synthetic data.
Authors: Md. Alamin Talukder, Md. Abu Layek, Mohsin Kazi, Md Ashraf Uddin, Sunil Aryal
Abstract: The worldwide COVID-19 pandemic has profoundly influenced the health and everyday experiences of individuals across the planet. It is a highly contagious respiratory disease requiring early and accurate detection to curb its rapid transmission. Initial testing methods primarily revolved around identifying the genetic composition of the coronavirus, exhibiting a relatively low detection rate and requiring a time-intensive procedure. To address this challenge, experts have suggested using radiological imagery, particularly chest X-rays, as a valuable approach within the diagnostic protocol. This study investigates the potential of leveraging radiographic imaging (X-rays) with deep learning algorithms to swiftly and precisely identify COVID-19 patients. The proposed approach elevates the detection accuracy by fine-tuning with appropriate layers on various established transfer learning models. The experimentation was conducted on a COVID-19 X-ray dataset containing 2000 images. The accuracy rates achieved were impressive of 100% for EfficientNetB4 model. The fine-tuned EfficientNetB4 achieved an excellent accuracy score, showcasing its potential as a robust COVID-19 detection model. Furthermore, EfficientNetB4 excelled in identifying Lung disease using Chest X-ray dataset containing 4,350 Images, achieving remarkable performance with an accuracy of 99.17%, precision of 99.13%, recall of 99.16%, and f1-score of 99.14%. These results highlight the promise of fine-tuned transfer learning for efficient lung detection through medical imaging, especially with X-ray images. This research offers radiologists an effective means of aiding rapid and precise COVID-19 diagnosis and contributes valuable assistance for healthcare professionals in accurately identifying affected patients.
Authors: Quang-Huy Nguyen, Jin Peng Zhou, Zhenzhen Liu, Khanh-Huyen Bui, Kilian Q. Weinberger, Wei-Lun Chao, Dung D. Le
Abstract: Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing significant challenges to model trustworthiness. Modern object detectors are typically overconfident, making it unreliable to use their predictions alone for OOD detection. To address this, we propose leveraging an auxiliary model as a complementary solution. Specifically, we utilize an off-the-shelf text-to-image generative model, such as Stable Diffusion, which is trained with objective functions distinct from those of discriminative object detectors. We hypothesize that this fundamental difference enables the detection of OOD objects by measuring inconsistencies between the models. Concretely, for a given detected object bounding box and its predicted in-distribution class label, we perform class-conditioned inpainting on the image with the object removed. If the object is OOD, the inpainted image is likely to deviate significantly from the original, making the reconstruction error a robust indicator of OOD status. Extensive experiments demonstrate that our approach consistently surpasses existing zero-shot and non-zero-shot OOD detection methods, establishing a robust framework for enhancing object detection systems in dynamic environments.
Authors: Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth
Abstract: Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative trajectories, and results in costly inference for diffusion models. To address these limitations, we introduce Neural Flow Diffusion Models (NFDM), a novel framework that enhances diffusion models by supporting a broader range of forward processes beyond the standard Gaussian. We also propose a novel parameterization technique for learning the forward process. Our framework provides an end-to-end, simulation-free optimization objective, effectively minimizing a variational upper bound on the negative log-likelihood. Experimental results demonstrate NFDM's strong performance, evidenced by state-of-the-art likelihood estimation. Furthermore, we investigate NFDM's capacity for learning generative dynamics with specific characteristics, such as deterministic straight lines trajectories, and demonstrate how the framework may be adopted for learning bridges between two distributions. The results underscores NFDM's versatility and its potential for a wide range of applications.
Authors: Jingwei Li, Jing Dong, Tianxing He, Jingzhao Zhang
Abstract: Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership inference attack (MIA) perspective. We first identify the limitation of applying existing MIA methods for proprietary diffusion models: the required access of internal U-nets. To address the above problem, we introduce a novel membership inference attack method that uses only the image-to-image variation API and operates without access to the model's internal U-net. Our method is based on the intuition that the model can more easily obtain an unbiased noise prediction estimate for images from the training set. By applying the API multiple times to the target image, averaging the outputs, and comparing the result to the original image, our approach can classify whether a sample was part of the training set. We validate our method using DDIM and Stable Diffusion setups and further extend both our approach and existing algorithms to the Diffusion Transformer architecture. Our experimental results consistently outperform previous methods.
Authors: Zhiyang Xu, Minqian Liu, Ying Shen, Joy Rimchala, Jiaxin Zhang, Qifan Wang, Yu Cheng, Lifu Huang
Abstract: Recent advancements in Vision-Language Models (VLMs) have led to the emergence of Vision-Language Generalists (VLGs) capable of understanding and generating both text and images. However, seamlessly generating an arbitrary sequence of text and images remains a challenging task for the current VLGs. One primary limitation lies in applying a unified architecture and the same set of parameters to simultaneously model discrete text tokens and continuous image features. Recent works attempt to tackle this fundamental problem by introducing modality-aware expert models. However, they employ identical architectures to process both text and images, disregarding the intrinsic inductive biases in these two modalities. In this work, we introduce MODALITY-SPECIALIZED SYNERGIZERS (MOSS), a novel design that efficiently optimizes existing unified architectures of VLGs with modality-specialized adaptation layers, i.e., a Convolutional LoRA for modeling the local priors of image patches and a Linear LoRA for processing sequential text. This design enables more effective modeling of modality-specific features while maintaining the strong cross-modal integration gained from pretraining. In addition, to improve the instruction-following capability on interleaved text-and-image generation, we introduce LEAFINSTRUCT, the first open-sourced interleaved instruction tuning dataset comprising 184,982 high-quality instances on more than 10 diverse domains. Extensive experiments show that VLGs integrated with M OSS achieve state-of-the-art performance, significantly surpassing baseline VLGs in complex interleaved generation tasks. Furthermore, our method exhibits strong generalizability on different VLGs.
Authors: Nebiyou Yismaw, Ulugbek S. Kamilov, M. Salman Asif
Abstract: Diffusion models can generate a variety of high-quality images by modeling complex data distributions. Trained diffusion models can also be very effective image priors for solving inverse problems. Most of the existing diffusion-based methods integrate data consistency steps by approximating the likelihood function within the diffusion reverse sampling process. In this paper, we show that the existing approximations are either insufficient or computationally inefficient. To address these issues, we propose a unified likelihood approximation method that incorporates a covariance correction term to enhance the performance and avoids propagating gradients through the diffusion model. The correction term, when integrated into the reverse diffusion sampling process, achieves better convergence towards the true data posterior for selected distributions and improves performance on real-world natural image datasets. Furthermore, we present an efficient way to factorize and invert the covariance matrix of the likelihood function for several inverse problems. Our comprehensive experiments demonstrate the effectiveness of our method over several existing approaches. Code available at https://github.com/CSIPlab/CoDPS.
Authors: Alan Papalia, Yulun Tian, David M. Rosen, Jonathan P. How, John J. Leonard
Abstract: This paper presents an overview of the Burer-Monteiro method (BM), a technique that has been applied to solve robot perception problems to certifiable optimality in real-time. BM is often used to solve semidefinite programming relaxations, which can be used to perform global optimization for non-convex perception problems. Specifically, BM leverages the low-rank structure of typical semidefinite programs to dramatically reduce the computational cost of performing optimization. This paper discusses BM in certifiable perception, with three main objectives: (i) to consolidate information from the literature into a unified presentation, (ii) to elucidate the role of the linear independence constraint qualification (LICQ), a concept not yet well-covered in certifiable perception literature, and (iii) to share practical considerations that are discussed among practitioners but not thoroughly covered in the literature. Our general aim is to offer a practical primer for applying BM towards certifiable perception.
Authors: Maryam Dialameh, Hossein Rajabzadeh, Moslem Sadeghi-Goughari, Jung Suk Sim, Hyock Ju Kwon
Abstract: Precise segmentation of papillary thyroid microcarcinoma (PTMC) during ultrasound-guided radiofrequency ablation (RFA) is critical for effective treatment but remains challenging due to acoustic artifacts, small lesion size, and anatomical variability. In this study, we propose \textbf{DualSwinUnet++}, a dual-decoder transformer-based architecture designed to enhance PTMC segmentation by incorporating thyroid gland context. DualSwinUnet++ employs independent linear projection heads for each decoder and a residual information flow mechanism that passes intermediate features from the first (thyroid) decoder to the second (PTMC) decoder via concatenation and transformation. These design choices allow the model to condition tumor prediction explicitly on gland morphology without shared gradient interference. Trained on a clinical ultrasound dataset with 691 annotated RFA images and evaluated against state-of-the-art models, DualSwinUnet++ achieves superior Dice and Jaccard scores while maintaining sub-200ms inference latency. The results demonstrate the model's suitability for near real-time surgical assistance and its effectiveness in improving segmentation accuracy in challenging PTMC cases.
Authors: Matthieu Terris, Ulugbek S. Kamilov, Thomas Moreau
Abstract: Selecting an appropriate prior to compensate for information loss due to the measurement operator is a fundamental challenge in imaging inverse problems. Implicit priors based on denoising neural networks have become central to widely-used frameworks such as Plug-and-Play (PnP) algorithms. In this work, we introduce Fixed-points of Restoration (FiRe) priors as a new framework for expanding the notion of priors in PnP to general restoration models beyond traditional denoising models. The key insight behind FiRe is that smooth images emerge as fixed points of the composition of a degradation operator with the corresponding restoration model. This enables us to derive an explicit formula for our implicit prior by quantifying invariance of images under this composite operation. Adopting this fixed-point perspective, we show how various restoration networks can effectively serve as priors for solving inverse problems. The FiRe framework further enables ensemble-like combinations of multiple restoration models as well as acquisition-informed restoration networks, all within a unified optimization approach. Experimental results validate the effectiveness of FiRe across various inverse problems, establishing a new paradigm for incorporating pretrained restoration models into PnP-like algorithms. Code available at https://github.com/matthieutrs/fire.
Authors: Andreas M\"uller, Denis Lukovnikov, Jonas Thietke, Asja Fischer, Erwin Quiring
Abstract: Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of watermarking techniques that are easy to implement and highly robust against various perturbations. However, our work demonstrates a fundamental security vulnerability of semantic watermarks. We show that attackers can leverage unrelated models, even with different latent spaces and architectures (UNet vs DiT), to perform powerful and realistic forgery attacks. Specifically, we design two watermark forgery attacks. The first imprints a targeted watermark into real images by manipulating the latent representation of an arbitrary image in an unrelated LDM to get closer to the latent representation of a watermarked image. We also show that this technique can be used for watermark removal. The second attack generates new images with the target watermark by inverting a watermarked image and re-generating it with an arbitrary prompt. Both attacks just need a single reference image with the target watermark. Overall, our findings question the applicability of semantic watermarks by revealing that attackers can easily forge or remove these watermarks under realistic conditions.
Authors: Haosheng Li, Weixin Mao, Weipeng Deng, Chenyu Meng, Haoqiang Fan, Tiancai Wang, Yoshie Osamu, Ping Tan, Hongan Wang, Xiaoming Deng
Abstract: Multi-hand semantic grasp generation aims to generate feasible and semantically appropriate grasp poses for different robotic hands based on natural language instructions. Although the task is highly valuable, due to the lack of multihand grasp datasets with fine-grained contact description between robotic hands and objects, it is still a long-standing difficult task. In this paper, we present Multi-GraspSet, the first large-scale multi-hand grasp dataset with automatically contact annotations. Based on Multi-GraspSet, we propose Multi-GraspLLM, a unified language-guided grasp generation framework, which leverages large language models (LLM) to handle variable-length sequences, generating grasp poses for diverse robotic hands in a single unified architecture. Multi-GraspLLM first aligns the encoded point cloud features and text features into a unified semantic space. It then generates grasp bin tokens that are subsequently converted into grasp pose for each robotic hand via hand-aware linear mapping. The experimental results demonstrate that our approach significantly outperforms existing methods in both real-world experiments and simulator. More information can be found on our project page https://multi-graspllm.github.io.
Authors: Ashay Athalye, Nishanth Kumar, Tom Silver, Yichao Liang, Jiuguang Wang, Tom\'as Lozano-P\'erez, Leslie Pack Kaelbling
Abstract: Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained vision language models (VLMs) to propose a large set of visual predicates potentially relevant for decision-making, and to evaluate those predicates directly from camera images. At training time, we pass the proposed predicates and demonstrations into an optimization-based model-learning algorithm to obtain an abstract symbolic world model that is defined in terms of a compact subset of the proposed predicates. At test time, given a novel goal in a novel setting, we use the VLM to construct a symbolic description of the current world state, and then use a search-based planning algorithm to find a sequence of low-level skills that achieves the goal. We demonstrate empirically across experiments in both simulation and the real world that our method can generalize aggressively, applying its learned world model to solve problems with a wide variety of object types, arrangements, numbers of objects, and visual backgrounds, as well as novel goals and much longer horizons than those seen at training time.
Authors: Yuewen Mei, Tong Nie, Jian Sun, Ye Tian
Abstract: Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for the deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are developed, in which behaviors of traffic participants are manipulated to induce safety-critical events. However, existing methods still face two limitations. First, identification of the adversarial participant directly impacts the effectiveness of the generation. However, the complexity of real-world scenarios, with numerous participants and diverse behaviors, makes identification challenging. Second, the potential of generated safety-critical scenarios to continuously improve ADS performance remains underexplored. To address these issues, we propose LLM-attacker: a closed-loop adversarial scenario generation framework leveraging large language models (LLMs). Specifically, multiple LLM agents are designed and coordinated to identify optimal attackers. Then, the trajectories of the attackers are optimized to generate adversarial scenarios. These scenarios are iteratively refined based on the performance of ADS, forming a feedback loop to improve ADS. Experimental results show that LLM-attacker can create more dangerous scenarios than other methods, and the ADS trained with it achieves a collision rate half that of training with normal scenarios. This indicates the ability of LLM-attacker to test and enhance the safety and robustness of ADS. Video demonstrations are provided at: https://drive.google.com/file/d/1Zv4V3iG7825oyiKbUwS2Y-rR0DQIE1ZA/view.
URLs: https://drive.google.com/file/d/1Zv4V3iG7825oyiKbUwS2Y-rR0DQIE1ZA/view.
Authors: Sahana Yadnakudige Subramanya, Ko Watanabe, Andreas Dengel, Shoya Ishimaru
Abstract: Human-in-the-loop (HITL) frameworks are increasingly recognized for their potential to improve annotation accuracy in emotion estimation systems by combining machine predictions with human expertise. This study focuses on integrating a high-performing image-based emotion model into a HITL annotation framework to evaluate the collaborative potential of human-machine interaction and identify the psychological and practical factors critical to successful collaboration. Specifically, we investigate how varying model reliability and cognitive framing influence human trust, cognitive load, and annotation behavior in HITL systems. We demonstrate that model reliability and psychological framing significantly impact annotators' trust, engagement, and consistency, offering insights into optimizing HITL frameworks. Through three experimental scenarios with 29 participants--baseline model reliability (S1), fabricated errors (S2), and cognitive bias introduced by negative framing (S3)--we analyzed behavioral and qualitative data. Reliable predictions in S1 yielded high trust and annotation consistency, while unreliable outputs in S2 led to increased critical evaluations but also heightened frustration and response variability. Negative framing in S3 revealed how cognitive bias influenced participants to perceive the model as more relatable and accurate, despite misinformation regarding its reliability. These findings highlight the importance of both reliable machine outputs and psychological factors in shaping effective human-machine collaboration. By leveraging the strengths of both human oversight and automated systems, this study establishes a scalable HITL framework for emotion annotation and lays the foundation for broader applications in adaptive learning and human-computer interaction.
Authors: Sebastin Santy, Prasanta Bhattacharya, Manoel Horta Ribeiro, Kelsey Allen, Sewoong Oh
Abstract: Progress in AI has relied on human-generated data, from annotator marketplaces to the wider Internet. However, the widespread use of large language models now threatens the quality and integrity of human-generated data on these very platforms. We argue that this issue goes beyond the immediate challenge of filtering AI-generated content -- it reveals deeper flaws in how data collection systems are designed. Existing systems often prioritize speed, scale, and efficiency at the cost of intrinsic human motivation, leading to declining engagement and data quality. We propose that rethinking data collection systems to align with contributors' intrinsic motivations -- rather than relying solely on external incentives -- can help sustain high-quality data sourcing at scale while maintaining contributor trust and long-term participation.
Authors: Aashish Anantha Ramakrishnan, Aadarsh Anantha Ramakrishnan, Dongwon Lee
Abstract: Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical correctness in downstream tasks, with limited emphasis on evaluating MLLMs' ability to interpret pragmatic cues and intermodal relationships. To address this gap, we assess the competency of MLLMs in performing Multimodal Discourse Analysis (MDA) using Coherence Relations. Our benchmark, CORDIAL, encompasses a broad spectrum of Coherence Relations across 3 different discourse domains at varying levels of granularity. Through our experiments on 10+ MLLMs employing different prompting strategies, we show that even top models like Gemini 1.5 Pro and GPT-4o fail to match the performance of simple classifier-based baselines. This study emphasizes the need to move beyond similarity-based metrics and adopt a discourse-driven framework for evaluating MLLMs, providing a more nuanced assessment of their capabilities. The benchmark and code are available at: https://aashish2000.github.io/CORDIAL/
Authors: Zichen Wen, Yifeng Gao, Shaobo Wang, Junyuan Zhang, Qintong Zhang, Weijia Li, Conghui He, Linfeng Zhang
Abstract: Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first defines an importance criterion for tokens and then prunes the unimportant vision tokens during inference. However, in this paper, we show that the importance is not an ideal indicator to decide whether a token should be pruned. Surprisingly, it usually results in inferior performance than random token pruning and leading to incompatibility to efficient attention computation operators.Instead, we propose DART (Duplication-Aware Reduction of Tokens), which prunes tokens based on its duplication with other tokens, leading to significant and training-free acceleration. Concretely, DART selects a small subset of pivot tokens and then retains the tokens with low duplication to the pivots, ensuring minimal information loss during token pruning. Experiments demonstrate that DART can prune 88.9% vision tokens while maintaining comparable performance, leading to a 1.99$\times$ and 2.99$\times$ speed-up in total time and prefilling stage, respectively, with good compatibility to efficient attention operators. Our codes are available at https://github.com/ZichenWen1/DART.
Authors: Li Qiao, Mahdi Boloursaz Mashhadi, Zhen Gao, Rahim Tafazolli, Mehdi Bennis, Dusit Niyato
Abstract: In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in generative semantic communications (GenSC). TokCom is a new paradigm, motivated by the recent success of generative foundation models and multimodal large language models (GFM/MLLMs), where the communication units are tokens, enabling efficient transformer-based token processing at the transmitter and receiver. In this paper, we introduce the potential opportunities and challenges of leveraging context in GenSC, explore how to integrate GFM/MLLMs-based token processing into semantic communication systems to leverage cross-modal context effectively at affordable complexity, present the key principles for efficient TokCom at various layers in future wireless networks. In a typical image semantic communication setup, we demonstrate a significant improvement of the bandwidth efficiency, achieved by TokCom by leveraging the context information among tokens. Finally, the potential research directions are identified to facilitate adoption of TokCom in future wireless networks.
Authors: Patryk Marsza{\l}ek, Maciej Rut, Piotr Kawa, Przemys{\l}aw Spurek, Piotr Syga
Abstract: Implicit neural representations (INR) have gained prominence for efficiently encoding multimedia data, yet their applications in audio signals remain limited. This study introduces the Kolmogorov-Arnold Network (KAN), a novel architecture using learnable activation functions, as an effective INR model for audio representation. KAN demonstrates superior perceptual performance over previous INRs, achieving the lowest Log-SpectralDistance of 1.29 and the highest Perceptual Evaluation of Speech Quality of 3.57 for 1.5 s audio. To extend KAN's utility, we propose FewSound, a hypernetwork-based architecture that enhances INR parameter updates. FewSound outperforms the state-of-the-art HyperSound, with a 33.3% improvement in MSE and 60.87% in SI-SNR. These results show KAN as a robust and adaptable audio representation with the potential for scalability and integration into various hypernetwork frameworks. The source code can be accessed at https://github.com/gmum/fewsound.git.
Authors: Ping Zhang, Zheda Mai, Quang-Huy Nguyen, Wei-Lun Chao
Abstract: Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remains unclear how SSL interacts with these pre-trained models. To address this gap, we develop new SSL benchmark datasets where frozen VFMs underperform and systematically evaluate representative SSL methods. We make a surprising observation: parameter-efficient fine-tuning (PEFT) using only labeled data often matches SSL performance, even without leveraging unlabeled data. This motivates us to revisit self-training, a conceptually simple SSL baseline, where we use the supervised PEFT model to pseudo-label unlabeled data for further training. To overcome the notorious issue of noisy pseudo-labels, we propose ensembling multiple PEFT approaches and VFM backbones to produce more robust pseudo-labels. Empirical results validate the effectiveness of this simple yet powerful approach, providing actionable insights into SSL with VFMs and paving the way for more scalable and practical semi-supervised learning in the era of foundation models.
Authors: Aashish Anantha Ramakrishnan, Aadarsh Anantha Ramakrishnan, Dongwon Lee
Abstract: Writing Assistants (e.g., Grammarly, Microsoft Copilot) traditionally generate diverse image captions by employing syntactic and semantic variations to describe image components. However, human-written captions prioritize conveying a central message alongside visual descriptions using pragmatic cues. To enhance caption diversity, it is essential to explore alternative ways of communicating these messages in conjunction with visual content. We propose RONA, a novel prompting strategy for Multi-modal Large Language Models (MLLM) that leverages Coherence Relations as a controllable axis for pragmatic variations. We demonstrate that RONA generates captions with better overall diversity and ground-truth alignment, compared to MLLM baselines across multiple domains. Our code is available at: https://github.com/aashish2000/RONA
Authors: Abhi Kamboj, Minh N. Do
Abstract: Multimodal alignment constructs a joint latent vector space where modalities representing the same concept map to neighboring latent vectors. We formulate this as an inverse problem and show that, under certain conditions, paired data from each modality can map to equivalent latent vectors, which we refer to as perfect alignment. When perfect alignment cannot be achieved, it can be approximated using the Singular Value Decomposition (SVD) of a multimodal data matrix. Experiments on synthetic multimodal Gaussian data verify the effectiveness of our perfect alignment method compared to a learned contrastive alignment method. We further demonstrate the practical application of cross-modal transfer for human action recognition, showing that perfect alignment significantly enhances the model's accuracy. We conclude by discussing how these findings can be applied to various modalities and tasks and the limitations of our method. We hope these findings inspire further exploration of perfect alignment and its applications in representation learning.
Authors: Siran Li, Chen Liu, Ruiyang Liu, Zhendong Wang, Gaofeng He, Yong-Lu Li, Xiaogang Jin, Huamin Wang
Abstract: Realistic digital garment modeling remains a labor-intensive task due to the intricate process of translating 2D sewing patterns into high-fidelity, simulation-ready 3D garments. We introduce GarmageNet, a unified generative framework that automates the creation of 2D sewing patterns, the construction of sewing relationships, and the synthesis of 3D garment initializations compatible with physics-based simulation. Central to our approach is Garmage, a novel garment representation that encodes each panel as a structured geometry image, effectively bridging the semantic and geometric gap between 2D structural patterns and 3D garment shapes. GarmageNet employs a latent diffusion transformer to synthesize panel-wise geometry images and integrates GarmageJigsaw, a neural module for predicting point-to-point sewing connections along panel contours. To support training and evaluation, we build GarmageSet, a large-scale dataset comprising over 10,000 professionally designed garments with detailed structural and style annotations. Our method demonstrates versatility and efficacy across multiple application scenarios, including scalable garment generation from multi-modal design concepts (text prompts, sketches, photographs), automatic modeling from raw flat sewing patterns, pattern recovery from unstructured point clouds, and progressive garment editing using conventional instructions-laying the foundation for fully automated, production-ready pipelines in digital fashion. Project page: https://style3d.github.io/garmagenet.
Authors: Junyi Cao, Evangelos Kalogerakis
Abstract: We present SOPHY, a generative model for 3D physics-aware shape synthesis. Unlike existing 3D generative models that focus solely on static geometry or 4D models that produce physics-agnostic animations, our method jointly synthesizes shape, texture, and material properties related to physics-grounded dynamics, making the generated objects ready for simulations and interactive, dynamic environments. To train our model, we introduce a dataset of 3D objects annotated with detailed physical material attributes, along with an efficient pipeline for material annotation. Our method enables applications such as text-driven generation of interactive, physics-aware 3D objects and single-image reconstruction of physically plausible shapes. Furthermore, our experiments show that jointly modeling shape and material properties enhances the realism and fidelity of the generated shapes, improving performance on both generative geometry and physical plausibility.
Authors: Ehsan Karami, Hamid Soltanian-Zadeh
Abstract: Knee osteoarthritis (KOA) is a common joint disease that causes pain and mobility issues. While MRI-based deep learning models have demonstrated superior performance in predicting total knee replacement (TKR) and disease progression, their generalizability remains challenging, particularly when applied to imaging data from different sources. In this study, we have shown that replacing batch normalization with instance normalization, using data augmentation, and applying contrastive loss improves model generalization in a baseline deep learning model for knee osteoarthritis (KOA) prediction. We trained and evaluated our model using MRI data from the Osteoarthritis Initiative (OAI) database, considering sagittal fat-suppressed intermediate-weighted turbo spin-echo (FS-IW-TSE) images as the source domain and sagittal fat-suppressed three-dimensional (3D) dual-echo in steady state (DESS) images as the target domain. The results demonstrate a statistically significant improvement in classification accuracy across both domains, with our approach outperforming the baseline model.
Authors: Junzhi Ning, Cheng Tang, Kaijin Zhou, Diping Song, Lihao Liu, Ming Hu, Wei Li, Yanzhou Su, Tianbing Li, Jiyao Liu, Yejin, Sheng Zhang, Yuanfeng Ji, Junjun He
Abstract: The scarcity of high-quality, labelled retinal imaging data, which presents a significant challenge in the development of machine learning models for ophthalmology, hinders progress in the field. To synthesise Colour Fundus Photographs (CFPs), existing methods primarily relying on predefined disease labels face significant limitations. However, current methods remain limited, thus failing to generate images for broader categories with diverse and fine-grained anatomical structures. To overcome these challenges, we first introduce an innovative pipeline that creates a large-scale, synthetic Caption-CFP dataset comprising 1.4 million entries, called RetinaLogos-1400k. Specifically, RetinaLogos-1400k uses large language models (LLMs) to describe retinal conditions and key structures, such as optic disc configuration, vascular distribution, nerve fibre layers, and pathological features. Furthermore, based on this dataset, we employ a novel three-step training framework, called RetinaLogos, which enables fine-grained semantic control over retinal images and accurately captures different stages of disease progression, subtle anatomical variations, and specific lesion types. Extensive experiments demonstrate state-of-the-art performance across multiple datasets, with 62.07% of text-driven synthetic images indistinguishable from real ones by ophthalmologists. Moreover, the synthetic data improves accuracy by 10%-25% in diabetic retinopathy grading and glaucoma detection, thereby providing a scalable solution to augment ophthalmic datasets.
Authors: Xinlong Chen, Yuanxing Zhang, Qiang Liu, Junfei Wu, Fuzheng Zhang, Tieniu Tan
Abstract: Large Vision-Language Models (LVLMs) have exhibited impressive capabilities across various visual tasks, yet they remain hindered by the persistent challenge of hallucinations. To address this critical issue, we propose Mixture of Decoding (MoD), a novel approach for hallucination mitigation that dynamically adapts decoding strategies by evaluating the correctness of the model's attention on image tokens. Specifically, MoD measures the consistency between outputs generated from the original image tokens and those derived from the model's attended image tokens, to distinguish the correctness aforementioned. If the outputs are consistent, indicating correct attention, MoD employs a complementary strategy to amplify critical information. Conversely, if the outputs are inconsistent, suggesting erroneous attention, MoD utilizes a contrastive strategy to suppress misleading information. Extensive experiments demonstrate that MoD significantly outperforms existing decoding methods across multiple mainstream benchmarks, effectively mitigating hallucinations in LVLMs. The code is available at https://github.com/xlchen0205/MoD.
Authors: Weihang Liu, Yuhui Zhong, Yuke Li, Xi Chen, Jiadi Cui, Honglong Zhang, Lan Xu, Xin Lou, Yujiao Shi, Jingyi Yu, Yingliang Zhang
Abstract: Accurate and efficient modeling of large-scale urban scenes is critical for applications such as AR navigation, UAV based inspection, and smart city digital twins. While aerial imagery offers broad coverage and complements limitations of ground-based data, reconstructing city-scale environments from such views remains challenging due to occlusions, incomplete geometry, and high memory demands. Recent advances like 3D Gaussian Splatting (3DGS) improve scalability and visual quality but remain limited by dense primitive usage, long training times, and poor suit ability for edge devices. We propose CityGo, a hybrid framework that combines textured proxy geometry with residual and surrounding 3D Gaussians for lightweight, photorealistic rendering of urban scenes from aerial perspectives. Our approach first extracts compact building proxy meshes from MVS point clouds, then uses zero order SH Gaussians to generate occlusion-free textures via image-based rendering and back-projection. To capture high-frequency details, we introduce residual Gaussians placed based on proxy-photo discrepancies and guided by depth priors. Broader urban context is represented by surrounding Gaussians, with importance-aware downsampling applied to non-critical regions to reduce redundancy. A tailored optimization strategy jointly refines proxy textures and Gaussian parameters, enabling real-time rendering of complex urban scenes on mobile GPUs with significantly reduced training and memory requirements. Extensive experiments on real-world aerial datasets demonstrate that our hybrid representation significantly reduces training time, achieving on average 1.4x speedup, while delivering comparable visual fidelity to pure 3D Gaussian Splatting approaches. Furthermore, CityGo enables real-time rendering of large-scale urban scenes on mobile consumer GPUs, with substantially reduced memory usage and energy consumption.
Authors: Xuanru Zhou, Jiarun Liu, Shoujun Yu, Hao Yang, Cheng Li, Tao Tan, Shanshan Wang
Abstract: In medical imaging, 4D MRI enables dynamic 3D visualization, yet the trade-off between spatial and temporal resolution requires prolonged scan time that can compromise temporal fidelity--especially during rapid, large-amplitude motion. Traditional approaches typically rely on registration-based interpolation to generate intermediate frames. However, these methods struggle with large deformations, resulting in misregistration, artifacts, and diminished spatial consistency. To address these challenges, we propose TSSC-Net, a novel framework that generates intermediate frames while preserving spatial consistency. To improve temporal fidelity under fast motion, our diffusion-based temporal super-resolution network generates intermediate frames using the start and end frames as key references, achieving 6x temporal super-resolution in a single inference step. Additionally, we introduce a novel tri-directional Mamba-based module that leverages long-range contextual information to effectively resolve spatial inconsistencies arising from cross-slice misalignment, thereby enhancing volumetric coherence and correcting cross-slice errors. Extensive experiments were performed on the public ACDC cardiac MRI dataset and a real-world dynamic 4D knee joint dataset. The results demonstrate that TSSC-Net can generate high-resolution dynamic MRI from fast-motion data while preserving structural fidelity and spatial consistency.
Authors: Sajjad Abdoli, Freeman Lewin, Gediminas Vasiliauskas, Fabian Schonholz
Abstract: The development of modern Artificial Intelligence (AI) models, particularly diffusion-based models employed in computer vision and image generation tasks, is undergoing a paradigmatic shift in development methodologies. Traditionally dominated by a "Model Centric" approach, in which performance gains were primarily pursued through increasingly complex model architectures and hyperparameter optimization, the field is now recognizing a more nuanced "Data-Centric" approach. This emergent framework foregrounds the quality, structure, and relevance of training data as the principal driver of model performance. To operationalize this paradigm shift, we introduce the DataSeeds.AI sample dataset (the "DSD"), initially comprised of approximately 10,610 high-quality human peer-ranked photography images accompanied by extensive multi-tier annotations. The DSD is a foundational computer vision dataset designed to usher in a new standard for commercial image datasets. Representing a small fraction of DataSeeds.AI's 100 million-plus image catalog, the DSD provides a scalable foundation necessary for robust commercial and multimodal AI development. Through this in-depth exploratory analysis, we document the quantitative improvements generated by the DSD on specific models against known benchmarks and make the code and the trained models used in our evaluation publicly available.