Authors: Meng Yang, Jun Chen, Wenping Gong, Longsheng Wei, Xin Tian
Abstract: Complicated nonlinear intensity differences, nonlinear local geometric distortions, noises and rotation transformation are main challenges in multimodal image matching. In order to solve these problems, we propose a method based on Frequency-domain Information of Local Energy Response called FILER. The core of FILER is the local energy response model based on frequency-domain information, which can overcome the effect of nonlinear intensity differences. To improve the robustness to local nonlinear geometric distortions and noises, we design a new edge structure enhanced feature detector and convolutional feature weighted descriptor, respectively. In addition, FILER overcomes the sensitivity of the frequency-domain information to the rotation angle and achieves rotation invariance. Extensive experiments multimodal image pairs show that FILER outperforms other state-of-the-art algorithms and has good robustness and universality.
Authors: Chamani Shiranthika, Zahra Hafezi Kafshgari, Hadi Hadizadeh, Parvaneh Saeedi
Abstract: Machine Learning (ML) and Deep Learning (DL) have shown significant promise in healthcare, particularly in medical image segmentation, which is crucial for accurate disease diagnosis and treatment planning. Despite their potential, challenges such as data privacy concerns, limited annotated data, and inadequate training data persist. Decentralized learning approaches such as federated learning (FL), split learning (SL), and split federated learning (SplitFed/SFL) address these issues effectively. This paper introduces "MedSegNet10," a publicly accessible repository designed for medical image segmentation using split-federated learning. MedSegNet10 provides a collection of pre-trained neural network architectures optimized for various medical image types, including microscopic images of human blastocysts, dermatoscopic images of skin lesions, and endoscopic images of lesions, polyps, and ulcers, with applications extending beyond these examples. By leveraging SplitFed's benefits, MedSegNet10 allows collaborative training on privately stored, horizontally split data, ensuring privacy and integrity. This repository supports researchers, practitioners, trainees, and data scientists, aiming to advance medical image segmentation while maintaining patient data privacy. The repository is available at: https://vault.sfu.ca/index.php/s/ryhf6t12O0sobuX (password upon request to the authors).
Authors: Alexander Swerdlow, Mihir Prabhudesai, Siddharth Gandhi, Deepak Pathak, Katerina Fragkiadaki
Abstract: Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, including improved control over quality versus diversity of generated samples, the ability to perform joint multimodal inpainting (across both text and image domains), and greater controllability in generation through guidance. Leveraging these benefits, we present the first Unified Multimodal Discrete Diffusion (UniDisc) model which is capable of jointly understanding and generating text and images for a variety of downstream tasks. We compare UniDisc to multimodal AR models, performing a scaling analysis and demonstrating that UniDisc outperforms them in terms of both performance and inference-time compute, enhanced controllability, editability, inpainting, and flexible trade-off between inference time and generation quality. Code and additional visualizations are available at https://unidisc.github.io.
Authors: Silin Gao, Sheryl Mathew, Li Mi, Sepideh Mamooler, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Syrielle Montariol, Antoine Bosselut
Abstract: Visual narrative generation transforms textual narratives into sequences of images illustrating the content of the text. However, generating visual narratives that are faithful to the input text and self-consistent across generated images remains an open challenge, due to the lack of knowledge constraints used for planning the stories. In this work, we propose a new benchmark, VinaBench, to address this challenge. Our benchmark annotates the underlying commonsense and discourse constraints in visual narrative samples, offering systematic scaffolds for learning the implicit strategies of visual storytelling. Based on the incorporated narrative constraints, we further propose novel metrics to closely evaluate the consistency of generated narrative images and the alignment of generations with the input textual narrative. Our results across three generative vision models demonstrate that learning with VinaBench's knowledge constraints effectively improves the faithfulness and cohesion of generated visual narratives.
Authors: Amaya Gallagher-Syed, Henry Senior, Omnia Alwazzan, Elena Pontarini, Michele Bombardieri, Costantino Pitzalis, Myles J. Lewis, Michael R. Barnes, Luca Rossi, Gregory Slabaugh
Abstract: The development of biologically interpretable and explainable models remains a key challenge in computational pathology, particularly for multistain immunohistochemistry (IHC) analysis. We present BioX-CPath, an explainable graph neural network architecture for whole slide image (WSI) classification that leverages both spatial and semantic features across multiple stains. At its core, BioX-CPath introduces a novel Stain-Aware Attention Pooling (SAAP) module that generates biologically meaningful, stain-aware patient embeddings. Our approach achieves state-of-the-art performance on both Rheumatoid Arthritis and Sjogren's Disease multistain datasets. Beyond performance metrics, BioX-CPath provides interpretable insights through stain attention scores, entropy measures, and stain interaction scores, that permit measuring model alignment with known pathological mechanisms. This biological grounding, combined with strong classification performance, makes BioX-CPath particularly suitable for clinical applications where interpretability is key. Source code and documentation can be found at: https://github.com/AmayaGS/BioX-CPath.
Authors: Venuri Amarasinghe (University of Moratuwa), Asini Jayakody (University of Moratuwa), Isun Randila (University of Moratuwa), Kalinga Bandara (University of Moratuwa), Chamuditha Jayanga Galappaththige (Queensland University of Technology), Ranga Rodrigo (University of Moratuwa)
Abstract: Semi-supervised domain generalization (SSDG) leverages a small fraction of labeled data alongside unlabeled data to enhance model generalization. Most of the existing SSDG methods rely on pseudo-labeling (PL) for unlabeled data, often assuming access to domain labels-a privilege not always available. However, domain shifts introduce domain noise, leading to inconsistent PLs that degrade model performance. Methods derived from FixMatch suffer particularly from lower PL accuracy, reducing the effectiveness of unlabeled data. To address this, we tackle the more challenging domain-label agnostic SSDG, where domain labels for unlabeled data are not available during training. First, we propose a feature modulation strategy that enhances class-discriminative features while suppressing domain-specific information. This modulation shifts features toward Similar Average Representations-a modified version of class prototypes-that are robust across domains, encouraging the classifier to distinguish between closely related classes and feature extractor to form tightly clustered, domain-invariant representations. Second, to mitigate domain noise and improve pseudo-label accuracy, we introduce a loss-scaling function that dynamically lowers the fixed confidence threshold for pseudo-labels, optimizing the use of unlabeled data. With these key innovations, our approach achieves significant improvements on four major domain generalization benchmarks-even without domain labels. We will make the code available.
Authors: Venkat Adithya Amula, Sunayana Samavedam, Saurabh Saini, Avani Gupta, Narayanan P J
Abstract: Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifications. Various triggers have been used, including semantic triggers that are easily realizable without requiring the attacker to manipulate the image. The emergence of generative AI has eased the generation of varied poisoned samples. Robustness across types of triggers is crucial to effective defense. We propose Prototype Guided Backdoor Defense (PGBD), a robust post-hoc defense that scales across different trigger types, including previously unsolved semantic triggers. PGBD exploits displacements in the geometric spaces of activations to penalize movements toward the trigger. This is done using a novel sanitization loss of a post-hoc fine-tuning step. The geometric approach scales easily to all types of attacks. PGBD achieves better performance across all settings. We also present the first defense against a new semantic attack on celebrity face images. Project page: \hyperlink{https://venkatadithya9.github.io/pgbd.github.io/}{this https URL}.
Authors: Daniel Etaat, Dvij Kalaria, Nima Rahmanian, Shankar Sastry
Abstract: Physical agility is a necessary skill in competitive table tennis, but by no means sufficient. Champions excel in this fast-paced and highly dynamic environment by anticipating their opponent's intent - buying themselves the necessary time to react. In this work, we take one step towards designing such an anticipatory agent. Previous works have developed systems capable of real-time table tennis gameplay, though they often do not leverage anticipation. Among the works that forecast opponent actions, their approaches are limited by dataset size and variety. Our paper contributes (1) a scalable system for reconstructing monocular video of table tennis matches in 3D and (2) an uncertainty-aware controller that anticipates opponent actions. We demonstrate in simulation that our policy improves the ball return rate against high-speed hits from 49.9% to 59.0% as compared to a baseline non-anticipatory policy.
Authors: David Wong, Bin Wang, Gorkem Durak, Marouane Tliba, Akshay Chaudhari, Aladine Chetouani, Ahmet Enis Cetin, Cagdas Topel, Nicolo Gennaro, Camila Lopes Vendrami, Tugce Agirlar Trabzonlu, Amir Ali Rahsepar, Laetitia Perronne, Matthew Antalek, Onural Ozturk, Gokcan Okur, Andrew C. Gordon, Ayis Pyrros, Frank H. Miller, Amir Borhani, Hatice Savas, Eric Hart, Drew Torigian, Jayaram K. Udupa, Elizabeth Krupinski, Ulas Bagci
Abstract: The demand for high-quality synthetic data for model training and augmentation has never been greater in medical imaging. However, current evaluations predominantly rely on computational metrics that fail to align with human expert recognition. This leads to synthetic images that may appear realistic numerically but lack clinical authenticity, posing significant challenges in ensuring the reliability and effectiveness of AI-driven medical tools. To address this gap, we introduce GazeVal, a practical framework that synergizes expert eye-tracking data with direct radiological evaluations to assess the quality of synthetic medical images. GazeVal leverages gaze patterns of radiologists as they provide a deeper understanding of how experts perceive and interact with synthetic data in different tasks (i.e., diagnostic or Turing tests). Experiments with sixteen radiologists revealed that 96.6% of the generated images (by the most recent state-of-the-art AI algorithm) were identified as fake, demonstrating the limitations of generative AI in producing clinically accurate images.
Authors: Tai D. Nguyen, Matthew C. Stamm
Abstract: While videos can be falsified in many different ways, most existing forensic networks are specialized to detect only a single manipulation type (e.g. deepfake, inpainting). This poses a significant issue as the manipulation used to falsify a video is not known a priori. To address this problem, we propose MVFNet - a multipurpose video forensics network capable of detecting multiple types of manipulations including inpainting, deepfakes, splicing, and editing. Our network does this by extracting and jointly analyzing a broad set of forensic feature modalities that capture both spatial and temporal anomalies in falsified videos. To reliably detect and localize fake content of all shapes and sizes, our network employs a novel Multi-Scale Hierarchical Transformer module to identify forensic inconsistencies across multiple spatial scales. Experimental results show that our network obtains state-of-the-art performance in general scenarios where multiple different manipulations are possible, and rivals specialized detectors in targeted scenarios.
Authors: Tai D. Nguyen, Aref Azizpour, Matthew C. Stamm
Abstract: The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to generalize to unseen generators due to reliance on features specific to known sources during training. To address this problem, we propose a novel approach that explicitly models forensic microstructures - subtle, pixel-level patterns unique to the image creation process. Using only real images in a self-supervised manner, we learn a set of diverse predictive filters to extract residuals that capture different aspects of these microstructures. By jointly modeling these residuals across multiple scales, we obtain a compact model whose parameters constitute a unique forensic self-description for each image. This self-description enables us to perform zero-shot detection of synthetic images, open-set source attribution of images, and clustering based on source without prior knowledge. Extensive experiments demonstrate that our method achieves superior accuracy and adaptability compared to competing techniques, advancing the state of the art in synthetic media forensics.
Authors: W. Riley Casper, Bobby Orozco
Abstract: The higher-order autocorrelations of integer-valued or rational-valued gridded data sets appear naturally in X-ray crystallography, and have applications in computer vision systems, correlation tomography, correlation spectroscopy, and pattern recognition. In this paper, we consider the problem of reconstructing a gridded data set from its higher-order autocorrelations. We describe an explicit reconstruction algorithm, and prove that the autocorrelations up to order 3r + 3 are always sufficient to determine the data up to translation, where r is the dimension of the grid. We also provide examples of rational-valued gridded data sets which are not determined by their autocorrelations up to order 3r + 2.
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 and error detection. 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: Yiqing Shen, Bohan Liu, Chenjia Li, Lalithkumar Seenivasan, Mathias Unberath
Abstract: Reasoning segmentation (RS) aims to identify and segment objects of interest based on implicit text queries. As such, RS is a catalyst for embodied AI agents, enabling them to interpret high-level commands without requiring explicit step-by-step guidance. However, current RS approaches rely heavily on the visual perception capabilities of multimodal large language models (LLMs), leading to several major limitations. First, they struggle with queries that require multiple steps of reasoning or those that involve complex spatial/temporal relationships. Second, they necessitate LLM fine-tuning, which may require frequent updates to maintain compatibility with contemporary LLMs and may increase risks of catastrophic forgetting during fine-tuning. Finally, being primarily designed for static images or offline video processing, they scale poorly to online video data. To address these limitations, we propose an agent framework that disentangles perception and reasoning for online video RS without LLM fine-tuning. Our innovation is the introduction of a just-in-time digital twin concept, where -- given an implicit query -- a LLM plans the construction of a low-level scene representation from high-level video using specialist vision models. We refer to this approach to creating a digital twin as "just-in-time" because the LLM planner will anticipate the need for specific information and only request this limited subset instead of always evaluating every specialist model. The LLM then performs reasoning on this digital twin representation to identify target objects. To evaluate our approach, we introduce a new comprehensive video reasoning segmentation benchmark comprising 200 videos with 895 implicit text queries. The benchmark spans three reasoning categories (semantic, spatial, and temporal) with three different reasoning chain complexity.
Authors: Mehraveh Javan Roshtkhari, Matthew Toews, Marco Pedersoli
Abstract: Monte-Carlo Tree Search (MCTS) is a powerful tool for many non-differentiable search related problems such as adversarial games. However, the performance of such approach highly depends on the order of the nodes that are considered at each branching of the tree. If the first branches cannot distinguish between promising and deceiving configurations for the final task, the efficiency of the search is exponentially reduced. In Neural Architecture Search (NAS), as only the final architecture matters, the visiting order of the branching can be optimized to improve learning. In this paper, we study the application of MCTS to NAS for image classification. We analyze several sampling methods and branching alternatives for MCTS and propose to learn the branching by hierarchical clustering of architectures based on their similarity. The similarity is measured by the pairwise distance of output vectors of architectures. Extensive experiments on two challenging benchmarks on CIFAR10 and ImageNet show that MCTS, if provided with a good branching hierarchy, can yield promising solutions more efficiently than other approaches for NAS problems.
Authors: Fan Qi, Yu Duan, Changsheng Xu
Abstract: Recent advances in text-guided diffusion models have revolutionized conditional image generation, yet they struggle to synthesize complex scenes with multiple objects due to imprecise spatial grounding and limited scalability. We address these challenges through two key modules: 1) Janus-Pro-driven Prompt Parsing, a prompt-layout parsing module that bridges text understanding and layout generation via a compact 1B-parameter architecture, and 2) MIGLoRA, a parameter-efficient plug-in integrating Low-Rank Adaptation (LoRA) into UNet (SD1.5) and DiT (SD3) backbones. MIGLoRA is capable of preserving the base model's parameters and ensuring plug-and-play adaptability, minimizing architectural intrusion while enabling efficient fine-tuning. To support a comprehensive evaluation, we create DescripBox and DescripBox-1024, benchmarks that span diverse scenes and resolutions. The proposed method achieves state-of-the-art performance on COCO and LVIS benchmarks while maintaining parameter efficiency, demonstrating superior layout fidelity and scalability for open-world synthesis.
Authors: Judy X Yang, Jing Wang, Zhuanfeng, Li, Chenhong Sui Zekun Long, Jun Zhou
Abstract: The integration of hyperspectral imaging (HSI) and Light Detection and Ranging (LiDAR) data provides complementary spectral and spatial information for remote sensing applications. While previous studies have explored the role of band selection and grouping in HSI classification, little attention has been given to how the spectral sequence or band order affects classification outcomes when fused with LiDAR. In this work, we systematically investigate the influence of band order on HSI-LiDAR fusion performance. Through extensive experiments, we demonstrate that band order significantly impacts classification accuracy, revealing a previously overlooked factor in fusion-based models. Motivated by this observation, we propose a novel fusion architecture that not only integrates HSI and LiDAR data but also learns from multiple band order configurations. The proposed method enhances feature representation by adaptively fusing different spectral sequences, leading to improved classification accuracy. Experimental results on the Houston 2013 and Trento datasets show that our approach outperforms state-of-the-art fusion models. Data and code are available at https://github.com/Judyxyang/HSLiNets.
Authors: Ooha Lakkadi Reddy
Abstract: This thesis employs a hybrid CNN-Transformer architecture, in conjunction with a detailed anthropological framework, to investigate potential historical connections between the visual morphology of the Indus Valley script and pictographic systems of the Tibetan-Yi Corridor. Through an ensemble methodology of three target scripts across 15 independently trained models, we demonstrate that Tibetan-Yi Corridor scripts exhibit approximately six-fold higher visual similarity to the Indus script (61.7%-63.5%) than to the Bronze Age Proto-Cuneiform (10.2%-10.9%) or Proto-Elamite (7.6%-8.7%) systems. Additionally and contrarily to our current understanding of the networks of the Indus Valley Civilization, the Indus script unexpectedly maps closer to Tibetan-Yi Corridor scripts, with a mean cosine similarity of 0.629, than to the aforementioned contemporaneous West Asian signaries, both of which recorded mean cosine similarities of 0.104 and 0.080 despite their close geographic proximity and evident trade relations. Across various dimensionality reduction practices and clustering methodologies, the Indus script consistently clusters closest to Tibetan-Yi Corridor scripts. Our computational results align with qualitative observations of specific pictorial parallels in numeral systems, gender markers, and key iconographic elements; this is further supported by archaeological evidence of sustained contact networks along the ancient Shu-Shendu road in tandem with the Indus Valley Civilization's decline, providing a plausible transmission pathway. While alternative explanations cannot be ruled out, the specificity and consistency of observed similarities challenge conventional narratives of isolated script development and suggest more complex ancient cultural transmission networks between South and East Asia than previously recognized.
Authors: Yusong Hu, Zichen Liang, Fei Yang, Qibin Hou, Xialei Liu, Ming-Ming Cheng
Abstract: Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in preserving learning stability during simple continual regression tasks, we set out to explore their potential in more complex continual learning scenarios. In this paper, we introduce the Kolmogorov-Arnold Classifier (KAC), a novel classifier developed for continual learning based on the KAN structure. We delve into the impact of KAN's spline functions and introduce Radial Basis Functions (RBF) for improved compatibility with continual learning. We replace linear classifiers with KAC in several recent approaches and conduct experiments across various continual learning benchmarks, all of which demonstrate performance improvements, highlighting the effectiveness and robustness of KAC in continual learning. The code is available at https://github.com/Ethanhuhuhu/KAC.
Authors: Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, J\"urgen Schmidhuber, Bernard Ghanem
Abstract: Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods either require specialized 4D representation or sophisticated optimization. In this paper, we present Sora3R, a novel framework that taps into the rich spatiotemporal priors of large-scale video diffusion models to directly infer 4D pointmaps from casual videos. Sora3R follows a two-stage pipeline: (1) we adapt a pointmap VAE from a pretrained video VAE, ensuring compatibility between the geometry and video latent spaces; (2) we finetune a diffusion backbone in combined video and pointmap latent space to generate coherent 4D pointmaps for every frame. Sora3R operates in a fully feedforward manner, requiring no external modules (e.g., depth, optical flow, or segmentation) or iterative global alignment. Extensive experiments demonstrate that Sora3R reliably recovers both camera poses and detailed scene geometry, achieving performance on par with state-of-the-art methods for dynamic 4D reconstruction across diverse scenarios.
Authors: Yun Zhu, Le Hui, Hang Yang, Jianjun Qian, Jin Xie, Jian Yang
Abstract: Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a unified sparse supervised 3D object detection method for both indoor and outdoor scenes through learning class prototypes to effectively utilize unlabeled objects. Specifically, we first propose a prototype-based object mining module that converts the unlabeled object mining into a matching problem between class prototypes and unlabeled features. By using optimal transport matching results, we assign prototype labels to high-confidence features, thereby achieving the mining of unlabeled objects. We then present a multi-label cooperative refinement module to effectively recover missed detections through pseudo label quality control and prototype label cooperation. Experiments show that our method achieves state-of-the-art performance under the one object per scene sparse supervised setting across indoor and outdoor datasets. With only one labeled object per scene, our method achieves about 78%, 90%, and 96% performance compared to the fully supervised detector on ScanNet V2, SUN RGB-D, and KITTI, respectively, highlighting the scalability of our method. Code is available at https://github.com/zyrant/CPDet3D.
Authors: Yuyin Chen, Yida Wang, Xueyang Zhang, Kun Zhan, Peng Jia, Yifei Zhan, Xianpeng Lang
Abstract: Urban scene reconstruction requires modeling both static infrastructure and dynamic elements while supporting diverse environmental conditions. We present \textbf{StyledStreets}, a multi-style street simulator that achieves instruction-driven scene editing with guaranteed spatial and temporal consistency. Building on a state-of-the-art Gaussian Splatting framework for street scenarios enhanced by our proposed pose optimization and multi-view training, our method enables photorealistic style transfers across seasons, weather conditions, and camera setups through three key innovations: First, a hybrid embedding scheme disentangles persistent scene geometry from transient style attributes, allowing realistic environmental edits while preserving structural integrity. Second, uncertainty-aware rendering mitigates supervision noise from diffusion priors, enabling robust training across extreme style variations. Third, a unified parametric model prevents geometric drift through regularized updates, maintaining multi-view consistency across seven vehicle-mounted cameras. Our framework preserves the original scene's motion patterns and geometric relationships. Qualitative results demonstrate plausible transitions between diverse conditions (snow, sandstorm, night), while quantitative evaluations show state-of-the-art geometric accuracy under style transfers. The approach establishes new capabilities for urban simulation, with applications in autonomous vehicle testing and augmented reality systems requiring reliable environmental consistency. Codes will be publicly available upon publication.
Authors: Teng Huang, Han Ding, Wenxin Sun, Cui Zhao, Ge Wang, Fei Wang, Kun Zhao, Zhi Wang, Wei Xi
Abstract: Wireless sensing systems, particularly those using mmWave technology, offer distinct advantages over traditional vision-based approaches, such as enhanced privacy and effectiveness in poor lighting conditions. These systems, leveraging FMCW signals, have shown success in human-centric applications like localization, gesture recognition, and so on. However, comprehensive mmWave datasets for diverse applications are scarce, often constrained by pre-processed signatures (e.g., point clouds or RA heatmaps) and inconsistent annotation formats. To overcome these limitations, we propose mmGen, a novel and generalized framework tailored for full-scene mmWave signal generation. By constructing physical signal transmission models, mmGen synthesizes human-reflected and environment-reflected mmWave signals from the constructed 3D meshes. Additionally, we incorporate methods to account for material properties, antenna gains, and multipath reflections, enhancing the realism of the synthesized signals. We conduct extensive experiments using a prototype system with commercial mmWave devices and Kinect sensors. The results show that the average similarity of Range-Angle and micro-Doppler signatures between the synthesized and real-captured signals across three different environments exceeds 0.91 and 0.89, respectively, demonstrating the effectiveness and practical applicability of mmGen.
Authors: Shuaiyu Zhang, Xun Lin, Rongxiang Zhang, Yu Bai, Yong Xu, Tao Tan, Xunbin Zheng, Zitong Yu
Abstract: The integration of pathologic images and genomic data for survival analysis has gained increasing attention with advances in multimodal learning. However, current methods often ignore biological characteristics, such as heterogeneity and sparsity, both within and across modalities, ultimately limiting their adaptability to clinical practice. To address these challenges, we propose AdaMHF: Adaptive Multimodal Hierarchical Fusion, a framework designed for efficient, comprehensive, and tailored feature extraction and fusion. AdaMHF is specifically adapted to the uniqueness of medical data, enabling accurate predictions with minimal resource consumption, even under challenging scenarios with missing modalities. Initially, AdaMHF employs an experts expansion and residual structure to activate specialized experts for extracting heterogeneous and sparse features. Extracted tokens undergo refinement via selection and aggregation, reducing the weight of non-dominant features while preserving comprehensive information. Subsequently, the encoded features are hierarchically fused, allowing multi-grained interactions across modalities to be captured. Furthermore, we introduce a survival prediction benchmark designed to resolve scenarios with missing modalities, mirroring real-world clinical conditions. Extensive experiments on TCGA datasets demonstrate that AdaMHF surpasses current state-of-the-art (SOTA) methods, showcasing exceptional performance in both complete and incomplete modality settings.
Authors: Jiajie Quan, Ao Tong, Yuxuan Cai, Xinwei He, Yulong Wang, Yang Zhou
Abstract: In multi-class unsupervised anomaly detection(MUAD), reconstruction-based methods learn to map input images to normal patterns to identify anomalous pixels. However, this strategy easily falls into the well-known "learning shortcut" issue when decoders fail to capture normal patterns and reconstruct both normal and abnormal samples naively. To address that, we propose to learn the input features in global and local manners, forcing the network to memorize the normal patterns more comprehensively. Specifically, we design a two-branch decoder block, named Omni-block. One branch corresponds to global feature learning, where we serialize two self-attention blocks but replace the query and (key, value) with learnable tokens, respectively, thus capturing global features of normal patterns concisely and thoroughly. The local branch comprises depth-separable convolutions, whose locality enables effective and efficient learning of local features for normal patterns. By stacking Omni-blocks, we build a framework, Omni-AD, to learn normal patterns of different granularity and reconstruct them progressively. Comprehensive experiments on public anomaly detection benchmarks show that our method outperforms state-of-the-art approaches in MUAD. Code is available at https://github.com/easyoo/Omni-AD.git.
Authors: Junjie Chen, Weilong Chen, Yifan Zuo, Yuming Fang
Abstract: Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling, and obtain interacted features from support and query via cross-attention. Hence, these works neglect to mine fine-grained and structure-aware (FGSA) features from both support and query images, which are crucial for pixel-level keypoint localization. To this end, we propose a novel yet concise framework, which recurrently mines FGSA features from both support and query images. Specifically, we design a FGSA mining module based on deformable attention mechanism. On the one hand, we mine fine-grained features by applying deformable attention head over multi-scale feature maps. On the other hand, we mine structure-aware features by offsetting the reference points of keypoints to their linked keypoints. By means of above module, we recurrently mine FGSA features from support and query images, and thus obtain better support features and query estimations. In addition, we propose to use mixup keypoints to pad various classes to a unified keypoint number, which could provide richer supervision than the zero padding used in existing works. We conduct extensive experiments and in-depth studies on large-scale MP-100 dataset, and outperform SOTA method dramatically (+3.2\%PCK@0.05). Code is avaiable at https://github.com/chenbys/FMMP.
Authors: Jinwei Qi, Chaonan Ji, Sheng Xu, Peng Zhang, Bang Zhang, Liefeng Bo
Abstract: Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies. However, existing methods primarily focus on real-time generation of head movements, but struggle to produce synchronized body motions that match these head actions. Additionally, achieving fine-grained control over the speaking style and nuances of facial expressions remains a challenge. To address these limitations, we introduce a novel framework for stylized real-time portrait video generation, enabling expressive and flexible video chat that extends from talking head to upper-body interaction. Our approach consists of the following two stages. The first stage involves efficient hierarchical motion diffusion models, that take both explicit and implicit motion representations into account based on audio inputs, which can generate a diverse range of facial expressions with stylistic control and synchronization between head and body movements. The second stage aims to generate portrait video featuring upper-body movements, including hand gestures. We inject explicit hand control signals into the generator to produce more detailed hand movements, and further perform face refinement to enhance the overall realism and expressiveness of the portrait video. Additionally, our approach supports efficient and continuous generation of upper-body portrait video in maximum 512 * 768 resolution at up to 30fps on 4090 GPU, supporting interactive video-chat in real-time. Experimental results demonstrate the capability of our approach to produce portrait videos with rich expressiveness and natural upper-body movements.
Authors: Yuhan Liu, Yixiong Zou, Yuhua Li, Ruixuan Li
Abstract: Cross-Domain Few-Shot Segmentation (CDFSS) is proposed to transfer the pixel-level segmentation capabilities learned from large-scale source-domain datasets to downstream target-domain datasets, with only a few annotated images per class. In this paper, we focus on a well-observed but unresolved phenomenon in CDFSS: for target domains, particularly those distant from the source domain, segmentation performance peaks at the very early epochs, and declines sharply as the source-domain training proceeds. We delve into this phenomenon for an interpretation: low-level features are vulnerable to domain shifts, leading to sharper loss landscapes during the source-domain training, which is the devil of CDFSS. Based on this phenomenon and interpretation, we further propose a method that includes two plug-and-play modules: one to flatten the loss landscapes for low-level features during source-domain training as a novel sharpness-aware minimization method, and the other to directly supplement target-domain information to the model during target-domain testing by low-level-based calibration. Extensive experiments on four target datasets validate our rationale and demonstrate that our method surpasses the state-of-the-art method in CDFSS signifcantly by 3.71% and 5.34% average MIoU in 1-shot and 5-shot scenarios, respectively.
Authors: Eugene Denteh, Andrews Danyo, Joshua Kofi Asamoah, Blessing Agyei Kyem, Twitchell Addai, Armstrong Aboah
Abstract: Transportation planning plays a critical role in shaping urban development, economic mobility, and infrastructure sustainability. However, traditional planning methods often struggle to accurately predict long-term urban growth and transportation demands. This may sometimes result in infrastructure demolition to make room for current transportation planning demands. This study integrates a Temporal Fusion Transformer to predict travel patterns from demographic data with a Generative Adversarial Network to predict future urban settings through satellite imagery. The framework achieved a 0.76 R-square score in travel behavior prediction and generated high-fidelity satellite images with a Structural Similarity Index of 0.81. The results demonstrate that integrating predictive analytics and spatial visualization can significantly improve the decision-making process, fostering more sustainable and efficient urban development. This research highlights the importance of data-driven methodologies in modern transportation planning and presents a step toward optimizing infrastructure placement, capacity, and long-term viability.
Authors: Samra Irshad, Seungkyu Lee, Nassir Navab, Hong Joo Lee, Seong Tae Kim
Abstract: The presence of adversarial examples in the physical world poses significant challenges to the deployment of Deep Neural Networks in safety-critical applications such as autonomous driving. Most existing methods for crafting physical-world adversarial examples are ad-hoc, relying on temporary modifications like shadows, laser beams, or stickers that are tailored to specific scenarios. In this paper, we introduce a new class of physical-world adversarial examples, AdvWT, which draws inspiration from the naturally occurring phenomenon of `wear and tear', an inherent property of physical objects. Unlike manually crafted perturbations, `wear and tear' emerges organically over time due to environmental degradation, as seen in the gradual deterioration of outdoor signboards. To achieve this, AdvWT follows a two-step approach. First, a GAN-based, unsupervised image-to-image translation network is employed to model these naturally occurring damages, particularly in the context of outdoor signboards. The translation network encodes the characteristics of damaged signs into a latent `damage style code'. In the second step, we introduce adversarial perturbations into the style code, strategically optimizing its transformation process. This manipulation subtly alters the damage style representation, guiding the network to generate adversarial images where the appearance of damages remains perceptually realistic, while simultaneously ensuring their effectiveness in misleading neural networks. Through comprehensive experiments on two traffic sign datasets, we show that AdvWT effectively misleads DNNs in both digital and physical domains. AdvWT achieves an effective attack success rate, greater robustness, and a more natural appearance compared to existing physical-world adversarial examples. Additionally, integrating AdvWT into training enhances a model's generalizability to real-world damaged signs.
Authors: Jiahao Lyu, Minghua Zhao, Jing Hu, Xuewen Huang, Yifei Chen, Shuangli Du
Abstract: Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in computer vision, exemplified by the Mamba model, demonstrates improved computational efficiency through selective scans and showcases the great potential for long-range modeling. Our study pioneers the application of Mamba to VAD, dubbed VADMamba, which is based on multi-task learning for frame prediction and optical flow reconstruction. Specifically, we propose the VQ-Mamba Unet (VQ-MaU) framework, which incorporates a Vector Quantization (VQ) layer and Mamba-based Non-negative Visual State Space (NVSS) block. Furthermore, two individual VQ-MaU networks separately predict frames and reconstruct corresponding optical flows, further boosting accuracy through a clip-level fusion evaluation strategy. Experimental results validate the efficacy of the proposed VADMamba across three benchmark datasets, demonstrating superior performance in inference speed compared to previous work. Code is available at https://github.com/jLooo/VADMamba.
Authors: Jingye Chen, Yuzhong Zhao, Yupan Huang, Lei Cui, Li Dong, Tengchao Lv, Qifeng Chen, Furu Wei
Abstract: Recent advances in generative models have significantly impacted game generation. However, despite producing high-quality graphics and adequately receiving player input, existing models often fail to maintain fundamental game properties such as numerical and spatial consistency. Numerical consistency ensures gameplay mechanics correctly reflect score changes and other quantitative elements, while spatial consistency prevents jarring scene transitions, providing seamless player experiences. In this paper, we revisit the paradigm of generative games to explore what truly constitutes a Model as a Game (MaaG) with a well-developed mechanism. We begin with an empirical study on ``Traveler'', a 2D game created by an LLM featuring minimalist rules yet challenging generative models in maintaining consistency. Based on the DiT architecture, we design two specialized modules: (1) a numerical module that integrates a LogicNet to determine event triggers, with calculations processed externally as conditions for image generation; and (2) a spatial module that maintains a map of explored areas, retrieving location-specific information during generation and linking new observations to ensure continuity. Experiments across three games demonstrate that our integrated modules significantly enhance performance on consistency metrics compared to baselines, while incurring minimal time overhead during inference.
Authors: Yimin Xu
Abstract: Despite the significant advancements in general image segmentation achieved by large-scale pre-trained foundation models (such as Meta's Segment Any-thing Model (SAM) series and DINOv2), their performance in specialized fields remains limited by two critical issues: the excessive training costs due to large model parameters, and the insufficient ability to represent specific domain characteristics. This paper proposes a multi-scale feature collabora-tion framework guided by DINOv2 for SAM2, with core innovations in three aspects: (1) Establishing a feature collaboration mechanism between DINOv2 and SAM2 backbones, where high-dimensional semantic features extracted by the self-supervised model guide multi-scale feature fusion; (2) Designing lightweight adapter modules and cross-modal, cross-layer feature fusion units to inject cross-domain knowledge while freezing the base model parameters; (3) Constructing a U-shaped network structure based on U-net, which utilizes attention mechanisms to achieve adaptive aggregation decoding of multi-granularity features. This framework surpasses existing state-of-the-art meth-ods in downstream tasks such as camouflage target detection and salient ob-ject detection, without requiring costly training processes. It provides a tech-nical pathway for efficient deployment of visual image segmentation, demon-strating significant application value in a wide range of downstream tasks and specialized fields within image segmentation.Project page: https://github.com/CheneyXuYiMin/SAM2DINO-Seg
Authors: Erika Mori, Yue Qiu, Hirokatsu Kataoka, Yoshimitsu Aoki
Abstract: Social intelligence, the ability to interpret emotions, intentions, and behaviors, is essential for effective communication and adaptive responses. As robots and AI systems become more prevalent in caregiving, healthcare, and education, the demand for AI that can interact naturally with humans grows. However, creating AI that seamlessly integrates multiple modalities, such as vision and speech, remains a challenge. Current video-based methods for social intelligence rely on general video recognition or emotion recognition techniques, often overlook the unique elements inherent in human interactions. To address this, we propose the Looped Video Debating (LVD) framework, which integrates Large Language Models (LLMs) with visual information, such as facial expressions and body movements, to enhance the transparency and reliability of question-answering tasks involving human interaction videos. Our results on the Social-IQ 2.0 benchmark show that LVD achieves state-of-the-art performance without fine-tuning. Furthermore, supplementary human annotations on existing datasets provide insights into the model's accuracy, guiding future improvements in AI-driven social intelligence.
Authors: Wenxuan Qiu, Chengxin Xie, Jingui Huang
Abstract: This paper presents an enhanced waste classification framework based on EfficientNetV2 to address challenges in data acquisition cost, generalization, and real-time performance. We propose a Channel-Efficient Attention (CE-Attention) module that mitigates feature loss during global pooling without introducing dimensional scaling, effectively enhancing critical feature extraction. Additionally, a lightweight multi-scale spatial feature extraction module (SAFM) is developed by integrating depthwise separable convolutions, significantly reducing model complexity. Comprehensive data augmentation strategies are further employed to improve generalization. Experiments on the Huawei Cloud waste classification dataset demonstrate that our method achieves a classification accuracy of 95.4\%, surpassing the baseline by 3.2\% and outperforming mainstream models. The results validate the effectiveness of our approach in balancing accuracy and efficiency for practical waste classification scenarios.
Authors: Yueying Gao, Dongliang Chang, Bingyao Yu, Haotian Qin, Lei Chen, Kongming Liang, Zhanyu Ma
Abstract: Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models makes it challenging to develop a generalizable forgery detection model. Moreover, since every pixel in an AI-generated image is synthesized, traditional saliency-based forgery explanation methods are not well suited for this task. To address these challenges, we propose modeling AI-generated image detection and explanation as a Forgery Detection and Reasoning task (FDR-Task), leveraging vision-language models (VLMs) to provide accurate detection through structured and reliable reasoning over forgery attributes. To facilitate this task, we introduce the Multi-Modal Forgery Reasoning dataset (MMFR-Dataset), a large-scale dataset containing 100K images across 10 generative models, with 10 types of forgery reasoning annotations, enabling comprehensive evaluation of FDR-Task. Additionally, we propose FakeReasoning, a forgery detection and reasoning framework with two key components. First, Forgery-Aligned Contrastive Learning enhances VLMs' understanding of forgery-related semantics through both cross-modal and intra-modal contrastive learning between images and forgery attribute reasoning. Second, a Classification Probability Mapper bridges the optimization gap between forgery detection and language modeling by mapping the output logits of VLMs to calibrated binary classification probabilities. Experiments across multiple generative models demonstrate that FakeReasoning not only achieves robust generalization but also outperforms state-of-the-art methods on both detection and reasoning tasks.
Authors: Alan Dao (Gia Tuan Dao), Norapat Buppodom
Abstract: Comprehending 3D environments is vital for intelligent systems in domains like robotics and autonomous navigation. Voxel grids offer a structured representation of 3D space, but extracting high-level semantic meaning remains challenging. This paper proposes a novel approach utilizing a Vision-Language Model (VLM) to extract "voxel semantics"-object identity, color, and location-from voxel data. Critically, instead of employing complex 3D networks, our method processes the voxel space by systematically slicing it along a primary axis (e.g., the Z-axis, analogous to CT scan slices). These 2D slices are then formatted and sequentially fed into the image encoder of a standard VLM. The model learns to aggregate information across slices and correlate spatial patterns with semantic concepts provided by the language component. This slice-based strategy aims to leverage the power of pre-trained 2D VLMs for efficient 3D semantic understanding directly from voxel representations.
Authors: Sibo Wu, Congrong Xu, Binbin Huang, Andreas Geiger, Anpei Chen
Abstract: Recently, 3D reconstruction and generation have demonstrated impressive novel view synthesis results, achieving high fidelity and efficiency. However, a notable conditioning gap can be observed between these two fields, e.g., scalable 3D scene reconstruction often requires densely captured views, whereas 3D generation typically relies on a single or no input view, which significantly limits their applications. We found that the source of this phenomenon lies in the misalignment between 3D constraints and generative priors. To address this problem, we propose a reconstruction-driven video diffusion model that learns to condition video frames on artifact-prone RGB-D renderings. Moreover, we propose a cyclical fusion pipeline that iteratively adds restoration frames from the generative model to the training set, enabling progressive expansion and addressing the viewpoint saturation limitations seen in previous reconstruction and generation pipelines. Our evaluation, including view synthesis from sparse view and masked input, validates the effectiveness of our approach.
Authors: Yishai Lavi, Leo Segre, Shai Avidan
Abstract: 3D Gaussian Splatting (3D-GS) has revolutionized novel view synthesis with its efficient, explicit representation. However, it lacks frequency interpretability, making it difficult to separate low-frequency structures from fine details. We introduce a frequency-decomposed 3D-GS framework that groups 3D Gaussians that correspond to subbands in the Laplacian Pyrmaids of the input images. Our approach enforces coherence within each subband (i.e., group of 3D Gaussians) through dedicated regularization, ensuring well-separated frequency components. We extend color values to both positive and negative ranges, allowing higher-frequency layers to add or subtract residual details. To stabilize optimization, we employ a progressive training scheme that refines details in a coarse-to-fine manner. Beyond interpretability, this frequency-aware design unlocks a range of practical benefits. Explicit frequency separation enables advanced 3D editing and stylization, allowing precise manipulation of specific frequency bands. It also supports dynamic level-of-detail control for progressive rendering, streaming, foveated rendering and fast geometry interaction. Through extensive experiments, we demonstrate that our method provides improved control and flexibility for emerging applications in scene editing and interactive rendering. Our code will be made publicly available.
Authors: Shuai Li, Jie Zhang, Yuang Qi, Kejiang Chen, Tianwei Zhang, Weiming Zhang, Nenghai Yu
Abstract: Large-scale image retrieval using deep hashing has become increasingly popular due to the exponential growth of image data and the remarkable feature extraction capabilities of deep neural networks (DNNs). However, deep hashing methods are vulnerable to malicious attacks, including adversarial and backdoor attacks. It is worth noting that these attacks typically involve altering the query images, which is not a practical concern in real-world scenarios. In this paper, we point out that even clean query images can be dangerous, inducing malicious target retrieval results, like undesired or illegal images. To the best of our knowledge, we are the first to study data \textbf{p}oisoning \textbf{a}ttacks against \textbf{d}eep \textbf{hash}ing \textbf{(\textit{PADHASH})}. Specifically, we first train a surrogate model to simulate the behavior of the target deep hashing model. Then, a strict gradient matching strategy is proposed to generate the poisoned images. Extensive experiments on different models, datasets, hash methods, and hash code lengths demonstrate the effectiveness and generality of our attack method.
Authors: Haoyu Zhao, Zhongang Qi, Cong Wang, Qingping Zheng, Guansong Lu, Fei Chen, Hang Xu, Zuxuan Wu
Abstract: Human image animation has recently gained significant attention due to advancements in generative models. However, existing methods still face two major challenges: (1) architectural limitations, most models rely on U-Net, which underperforms compared to the MM-DiT; and (2) the neglect of textual information, which can enhance controllability. In this work, we introduce DynamiCtrl, a novel framework that not only explores different pose-guided control structures in MM-DiT, but also reemphasizes the crucial role of text in this task. Specifically, we employ a Shared VAE encoder for both reference images and driving pose videos, eliminating the need for an additional pose encoder and simplifying the overall framework. To incorporate pose features into the full attention blocks, we propose Pose-adaptive Layer Norm (PadaLN), which utilizes adaptive layer normalization to encode sparse pose features. The encoded features are directly added to the visual input, preserving the spatiotemporal consistency of the backbone while effectively introducing pose control into MM-DiT. Furthermore, within the full attention mechanism, we align textual and visual features to enhance controllability. By leveraging text, we not only enable fine-grained control over the generated content, but also, for the first time, achieve simultaneous control over both background and motion. Experimental results verify the superiority of DynamiCtrl on benchmark datasets, demonstrating its strong identity preservation, heterogeneous character driving, background controllability, and high-quality synthesis. The project page is available at https://gulucaptain.github.io/DynamiCtrl/.
Authors: Mohamed Lamine Mekhalfi, Paul Chippendale, Francisco Fraile, Marcos Rico
Abstract: Orange grading is a crucial step in the fruit industry, as it helps to sort oranges according to different criteria such as size, quality, ripeness, and health condition, ensuring safety for human consumption and better price allocation and client satisfaction. Automated grading enables faster processing, precision, and reduced human labor. In this paper, we implement a deep learning-based solution for orange grading via machine vision. Unlike typical grading systems that analyze fruits from a single view, we capture multiview images of each single orange in order to enable a richer representation. Afterwards, we compose the acquired images into one collage. This enables the analysis of the whole orange skin. We train a convolutional neural network (CNN) on the composed images to grade the oranges into three classes, namely good, bad, and undefined. We also evaluate the performance with two different CNNs (ResNet-18 and SqueezeNet). We show experimentally that multi-view grading is superior to single view grading.
Authors: Zhaokai Wang, Chenxi Bao, Le Zhuo, Jingrui Han, Yang Yue, Yihong Tang, Victor Shea-Jay Huang, Yue Liao
Abstract: Vision-to-music Generation, including video-to-music and image-to-music tasks, is a significant branch of multimodal artificial intelligence demonstrating vast application prospects in fields such as film scoring, short video creation, and dance music synthesis. However, compared to the rapid development of modalities like text and images, research in vision-to-music is still in its preliminary stage due to its complex internal structure and the difficulty of modeling dynamic relationships with video. Existing surveys focus on general music generation without comprehensive discussion on vision-to-music. In this paper, we systematically review the research progress in the field of vision-to-music generation. We first analyze the technical characteristics and core challenges for three input types: general videos, human movement videos, and images, as well as two output types of symbolic music and audio music. We then summarize the existing methodologies on vision-to-music generation from the architecture perspective. A detailed review of common datasets and evaluation metrics is provided. Finally, we discuss current challenges and promising directions for future research. We hope our survey can inspire further innovation in vision-to-music generation and the broader field of multimodal generation in academic research and industrial applications. To follow latest works and foster further innovation in this field, we are continuously maintaining a GitHub repository at https://github.com/wzk1015/Awesome-Vision-to-Music-Generation.
URLs: https://github.com/wzk1015/Awesome-Vision-to-Music-Generation.
Authors: Jizhou Han, Chenhao Ding, Yuhang He, Songlin Dong, Qiang Wang, Xinyuan Gao, Yihong Gong
Abstract: Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL methods often require fine-tuning parameters with limited new class data and suffer from a separation between learning new classes and utilizing old knowledge. Inspired by the analogical learning mechanisms of the human brain, we propose a novel analogical generative method. Our approach includes the Brain-Inspired Analogical Generator (BiAG), which derives new class weights from existing classes without parameter fine-tuning during incremental stages. BiAG consists of three components: Weight Self-Attention Module (WSA), Weight & Prototype Analogical Attention Module (WPAA), and Semantic Conversion Module (SCM). SCM uses Neural Collapse theory for semantic conversion, WSA supplements new class weights, and WPAA computes analogies to generate new class weights. Experiments on miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our method achieves higher final and average accuracy compared to SOTA methods.
Authors: Wencheng Han, Dongqian Guo, Xiao Chen, Pang Lyu, Yi Jin, Jianbing Shen
Abstract: Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding the introduction of noise information. Our work is based on a key finding that even artifact-affected ordinary CT sequences contain sufficient information to discern detailed structures. The challenge lies in the inability to clearly represent this information. To address this issue, we developed an Alignment Framework that adjusts the representation of ordinary CT images to match GSI CT sequences. GSI is an advanced imaging technique using multiple energy levels to mitigate artifacts caused by metal implants. By aligning the representation to GSI data, we can effectively suppress metal artifacts while clearly revealing detailed structure, without introducing extraneous information into CT sequences. To facilitate the application, we propose a new dataset, Artifacts-GSI, captured from real patients with metal implants, and establish a new benchmark based on this dataset. Experimental results show that our method significantly reduces metal artifacts and greatly enhances the readability of CT slices. All our code and data are available at: https://um-lab.github.io/GSI-MAR/
Authors: Yunusa Haruna, Adamu Lawan
Abstract: Capturing long-range dependencies efficiently is essential for visual recognition tasks, yet existing methods face limitations. Convolutional neural networks (CNNs) struggle with restricted receptive fields, while Vision Transformers (ViTs) achieve global context and long-range modeling at a high computational cost. State-space models (SSMs) offer an alternative, but their application in vision remains underexplored. This work introduces vGamba, a hybrid vision backbone that integrates SSMs with attention mechanisms to enhance efficiency and expressiveness. At its core, the Gamba bottleneck block that includes, Gamba Cell, an adaptation of Mamba for 2D spatial structures, alongside a Multi-Head Self-Attention (MHSA) mechanism and a Gated Fusion Module for effective feature representation. The interplay of these components ensures that vGamba leverages the low computational demands of SSMs while maintaining the accuracy of attention mechanisms for modeling long-range dependencies in vision tasks. Additionally, the Fusion module enables seamless interaction between these components. Extensive experiments on classification, detection, and segmentation tasks demonstrate that vGamba achieves a superior trade-off between accuracy and computational efficiency, outperforming several existing models.
Authors: Ming Yan, Xincheng Lin, Yuhua Luo, Shuqi Fan, Yudi Dai, Qixin Zhong, Lincai Zhong, Yuexin Ma, Lan Xu, Chenglu Wen, Siqi Shen, Cheng Wang
Abstract: Human Motion Recovery (HMR) research mainly focuses on ground-based motions such as running. The study on capturing climbing motion, an off-ground motion, is sparse. This is partly due to the limited availability of climbing motion datasets, especially large-scale and challenging 3D labeled datasets. To address the insufficiency of climbing motion datasets, we collect AscendMotion, a large-scale well-annotated, and challenging climbing motion dataset. It consists of 412k RGB, LiDAR frames, and IMU measurements, including the challenging climbing motions of 22 skilled climbing coaches across 12 different rock walls. Capturing the climbing motions is challenging as it requires precise recovery of not only the complex pose but also the global position of climbers. Although multiple global HMR methods have been proposed, they cannot faithfully capture climbing motions. To address the limitations of HMR methods for climbing, we propose ClimbingCap, a motion recovery method that reconstructs continuous 3D human climbing motion in a global coordinate system. One key insight is to use the RGB and LiDAR modalities to separately reconstruct motions in camera coordinates and global coordinates and to optimize them jointly. We demonstrate the quality of the AscendMotion dataset and present promising results from ClimbingCap. The AscendMotion dataset and source code release publicly at \href{this link}{http://www.lidarhumanmotion.net/climbingcap/}
Authors: Zhaoyi Yan, Kangjun Liu, Qixiang Ye
Abstract: Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfer of knowledge from complex models to lightweight counterparts. Traditional distillation approaches focus on transferring knowledge at the instance level, but fail to capture nuanced semantic relationships within the data. In response, this paper introduces a novel methodology, Semantics-based Relation Knowledge Distillation (SeRKD), which reimagines knowledge distillation through a semantics-relation lens among each sample. By leveraging semantic components, \ie, superpixels, SeRKD enables a more comprehensive and context-aware transfer of knowledge, which skillfully integrates superpixel-based semantic extraction with relation-based knowledge distillation for a sophisticated model compression and distillation. Particularly, the proposed method is naturally relevant in the domain of Vision Transformers (ViTs), where visual tokens serve as fundamental units of representation. Experimental evaluations on benchmark datasets demonstrate the superiority of SeRKD over existing methods, underscoring its efficacy in enhancing model performance and generalization capabilities.
Authors: Hiroya Makino, Takahiro Yamaguchi, Hiroyuki Sakai
Abstract: We propose a novel, zero-shot image generation technique called "Visual Concept Blending" that provides fine-grained control over which features from multiple reference images are transferred to a source image. If only a single reference image is available, it is difficult to isolate which specific elements should be transferred. However, using multiple reference images, the proposed approach distinguishes between common and unique features by selectively incorporating them into a generated output. By operating within a partially disentangled Contrastive Language-Image Pre-training (CLIP) embedding space (from IP-Adapter), our method enables the flexible transfer of texture, shape, motion, style, and more abstract conceptual transformations without requiring additional training or text prompts. We demonstrate its effectiveness across a diverse range of tasks, including style transfer, form metamorphosis, and conceptual transformations, showing how subtle or abstract attributes (e.g., brushstroke style, aerodynamic lines, and dynamism) can be seamlessly combined into a new image. In a user study, participants accurately recognized which features were intended to be transferred. Its simplicity, flexibility, and high-level control make Visual Concept Blending valuable for creative fields such as art, design, and content creation, where combining specific visual qualities from multiple inspirations is crucial.
Authors: Hanyue Tu, Siqi Wu, Li Li, Wengang Zhou, Houqiang Li
Abstract: Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distortion performance at high bit rates and restricts their flexibility of rate adaptation. In this paper, we present a variable-rate image compression model based on invertible transform to overcome these limitations. Specifically, we design a lightweight multi-scale invertible neural network, which bijectively maps the input image into multi-scale latent representations. To improve the compression efficiency, a multi-scale spatial-channel context model with extended gain units is devised to estimate the entropy of the latent representation from high to low levels. Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods, and remains competitive with recent multi-model approaches. Notably, our method is the first learned image compression solution that outperforms VVC across a very wide range of bit rates using a single model, especially at high bit rates.The source code is available at \href{https://github.com/hytu99/MSINN-VRLIC}{https://github.com/hytu99/MSINN-VRLIC}.
URLs: https://github.com/hytu99/MSINN-VRLIC, https://github.com/hytu99/MSINN-VRLIC
Authors: Dongchen Lu, Yuyao Sun, Zilu Zhang, Leping Huang, Jianliang Zeng, Mao Shu, Huo Cao
Abstract: Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand for computational resources and time. In this paper, we propose InternVL-X, which outperforms the InternVL model in both performance and efficiency by incorporating three visual token compression methods. First, we propose a novel vision-language projector, PVTC. This component integrates adjacent visual embeddings to form a local query and utilizes the transformed CLS token as a global query, then performs point-to-region cross-attention through these local and global queries to more effectively convert visual features. Second, we present a layer-wise visual token compression module, LVTC, which compresses tokens in the LLM shallow layers and then expands them through upsampling and residual connections in the deeper layers. This significantly enhances the model computational efficiency. Futhermore, we propose an efficient high resolution slicing method, RVTC, which dynamically adjusts the number of visual tokens based on image area or length filtering. RVTC greatly enhances training efficiency with only a slight reduction in performance. By utilizing 20% or fewer visual tokens, InternVL-X achieves state-of-the-art performance on 7 public MLLM benchmarks, and improves the average metric by 2.34% across 12 tasks.
Authors: Zixu Li, Zhiheng Fu, Yupeng Hu, Zhiwei Chen, Haokun Wen, Liqiang Nie
Abstract: Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired alterations. However, existing CIR datasets predominantly employ coarse-grained modification text (CoarseMT), which inadequately captures fine-grained retrieval intents. This limitation introduces two key challenges: (1) ignoring detailed differences leads to imprecise positive samples, and (2) greater ambiguity arises when retrieving visually similar images. These issues degrade retrieval accuracy, necessitating manual result filtering or repeated queries. To address these limitations, we develop a robust fine-grained CIR data annotation pipeline that minimizes imprecise positive samples and enhances CIR systems' ability to discern modification intents accurately. Using this pipeline, we refine the FashionIQ and CIRR datasets to create two fine-grained CIR datasets: Fine-FashionIQ and Fine-CIRR. Furthermore, we introduce FineCIR, the first CIR framework explicitly designed to parse the modification text. FineCIR effectively captures fine-grained modification semantics and aligns them with ambiguous visual entities, enhancing retrieval precision. Extensive experiments demonstrate that FineCIR consistently outperforms state-of-the-art CIR baselines on both fine-grained and traditional CIR benchmark datasets. Our FineCIR code and fine-grained CIR datasets are available at https://github.com/SDU-L/FineCIR.git.
Authors: Zerui Chen, Rolandos Alexandros Potamias, Shizhe Chen, Cordelia Schmid
Abstract: Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are time-consuming to generate explicit 3D shapes. While more recent methods directly reconstruct point clouds with diffusion models, the multi-step denoising makes high-resolution reconstruction inefficient. To address these limitations, we propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method follows a coarse-to-fine strategy, first generating a sparse point cloud from the image and progressively refining it into a dense representation using pixel-aligned image features. To enhance reconstruction accuracy, we integrate image features with 3D hand geometry to jointly predict the object point cloud and its pose relative to the hand. Our model is trained end-to-end for optimal performance. Experimental results on both synthetic and real datasets demonstrate that our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
Authors: Ling Feng, Tianyu Xie, Wei Ma, Ruijie Fu, Yingxiao Zhang, Jun Li, Bei Zhou
Abstract: The modernization of smart farming is a way to improve agricultural production efficiency, and improve the agricultural production environment. Although many large models have achieved high accuracy in the task of object recognition and segmentation, they cannot really be put into use in the farming industry due to their own poor interpretability and limitations in computational volume. In this paper, we built AnYue Shelduck Dateset, which contains a total of 1951 Shelduck datasets, and performed target detection and segmentation annotation with the help of professional annotators. Based on AnYue ShelduckDateset, this paper describes DuckProcessing, an efficient and powerful module for duck identification based on real shelduckfarms. First of all, using the YOLOv8 module designed to divide the mahjong between them, Precision reached 98.10%, Recall reached 96.53% and F1 score reached 0.95 on the test set. Again using the DuckSegmentation segmentation model, DuckSegmentation reached 96.43% mIoU. Finally, the excellent DuckSegmentation was used as the teacher model, and through knowledge distillation, Deeplabv3 r50 was used as the student model, and the final student model achieved 94.49% mIoU on the test set. The method provides a new way of thinking in practical sisal duck smart farming.
Authors: Yehui Shen, Lei Zhang, Qingqiu Li, Xiongwei Zhao, Yue Wang, Huimin Lu, Xieyuanli Chen
Abstract: Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at \href{https://github.com/nubot-nudt/UGNA-VPR}{https://github.com/nubot-nudt/UGNA-VPR}.
URLs: https://github.com/nubot-nudt/UGNA-VPR, https://github.com/nubot-nudt/UGNA-VPR
Authors: Zhenxiang Ma, Zhenyu Yang, Miao Tao, Yuanzhen Zhou, Zeyu He, Yuchang Zhang, Rong Fu, Hengjie Li
Abstract: 3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented reality, and the metaverse. Recent advancements such as Neural Radiance Fields(NeRF) and 3D Gaussian Splatting (3DGS) have transformed the field, yet traditional deep learning frameworks struggle to meet the increasing demands for scene quality and scale. This paper introduces LandMarkSystem, a novel computing framework designed to enhance multi-scale scene reconstruction and rendering. By leveraging a componentized model adaptation layer, LandMarkSystem supports various NeRF and 3DGS structures while optimizing computational efficiency through distributed parallel computing and model parameter offloading. Our system addresses the limitations of existing frameworks, providing dedicated operators for complex 3D sparse computations, thus facilitating efficient training and rapid inference over extensive scenes. Key contributions include a modular architecture, a dynamic loading strategy for limited resources, and proven capabilities across multiple representative algorithms.This comprehensive solution aims to advance the efficiency and effectiveness of 3D reconstruction tasks.To facilitate further research and collaboration, the source code and documentation for the LandMarkSystem project are publicly available in an open-source repository, accessing the repository at: https://github.com/InternLandMark/LandMarkSystem.
Authors: Bo\v{r}ek Reich, Matej Kunda, Fedor Zolotarev, Tuomas Eerola, Pavel Zem\v{c}\'ik, Tomi Kauppi
Abstract: We propose a novel, good-quality, and less demanding method for detecting knots on the surface of wooden logs using multimodal data fusion. Knots are a primary factor affecting the quality of sawn timber, making their detection fundamental to any timber grading or cutting optimization system. While X-ray computed tomography provides accurate knot locations and internal structures, it is often too slow or expensive for practical use. An attractive alternative is to use fast and cost-effective log surface measurements, such as laser scanners or RGB cameras, to detect surface knots and estimate the internal structure of wood. However, due to the small size of knots and noise caused by factors, such as bark and other natural variations, detection accuracy often remains low when only one measurement modality is used. In this paper, we demonstrate that by using a data fusion pipeline consisting of separate streams for RGB and point cloud data, combined by a late fusion module, higher knot detection accuracy can be achieved compared to using either modality alone. We further propose a simple yet efficient sawing angle optimization method that utilizes surface knot detections and cross-correlation to minimize the amount of unwanted arris knots, demonstrating its benefits over randomized sawing angles.
Authors: Hamadi Chihaoui, Paolo Favaro
Abstract: Supervised training for real-world denoising presents challenges due to the difficulty of collecting large datasets of paired noisy and clean images. Recent methods have attempted to address this by utilizing unpaired datasets of clean and noisy images. Some approaches leverage such unpaired data to train denoisers in a supervised manner by generating synthetic clean-noisy pairs. However, these methods often fall short due to the distribution gap between synthetic and real noisy images. To mitigate this issue, we propose a solution based on input sparsification, specifically using random input masking. Our method, which we refer to as Mask, Inpaint and Denoise (MID), trains a denoiser to simultaneously denoise and inpaint synthetic clean-noisy pairs. On one hand, input sparsification reduces the gap between synthetic and real noisy images. On the other hand, an inpainter trained in a supervised manner can still accurately reconstruct sparse inputs by predicting missing clean pixels using the remaining unmasked pixels. Our approach begins with a synthetic Gaussian noise sampler and iteratively refines it using a noise dataset derived from the denoiser's predictions. The noise dataset is created by subtracting predicted pseudo-clean images from real noisy images at each iteration. The core intuition is that improving the denoiser results in a more accurate noise dataset and, consequently, a better noise sampler. We validate our method through extensive experiments on real-world noisy image datasets, demonstrating competitive performance compared to existing unsupervised denoising methods.
Authors: Marshall Thomas, Edward Fish, Richard Bowden
Abstract: Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements and facial expressions. This task is especially challenging due to the absence of auditory information and the inherent ambiguity when visually distinguishing phonemes that have overlapping visemes where different phonemes appear identical on the lips. Current methods typically attempt to predict words or characters directly from these visual cues, but this approach frequently encounters high error rates due to coarticulation effects and viseme ambiguity. We propose a novel two-stage, phoneme-centric framework for Visual Automatic Speech Recognition (V-ASR) that addresses these longstanding challenges. First, our model predicts a compact sequence of phonemes from visual inputs using a Video Transformer with a CTC head, thereby reducing the task complexity and achieving robust speaker invariance. This phoneme output then serves as the input to a fine-tuned Large Language Model (LLM), which reconstructs coherent words and sentences by leveraging broader linguistic context. Unlike existing methods that either predict words directly-often faltering on visually similar phonemes-or rely on large-scale multimodal pre-training, our approach explicitly encodes intermediate linguistic structure while remaining highly data efficient. We demonstrate state-of-the-art performance on two challenging datasets, LRS2 and LRS3, where our method achieves significant reductions in Word Error Rate (WER) achieving a SOTA WER of 18.7 on LRS3 despite using 99.4% less labelled data than the next best approach.
Authors: Hamadi Chihaoui, Paolo Favaro
Abstract: Zero-shot image restoration (IR) methods based on pretrained diffusion models have recently achieved significant success. These methods typically require at least a parametric form of the degradation model. However, in real-world scenarios, the degradation may be too complex to define explicitly. To handle this general case, we introduce the Diffusion Image Prior (DIIP). We take inspiration from the Deep Image Prior (DIP)[16], since it can be used to remove artifacts without the need for an explicit degradation model. However, in contrast to DIP, we find that pretrained diffusion models offer a much stronger prior, despite being trained without knowledge from corrupted data. We show that, the optimization process in DIIP first reconstructs a clean version of the image before eventually overfitting to the degraded input, but it does so for a broader range of degradations than DIP. In light of this result, we propose a blind image restoration (IR) method based on early stopping, which does not require prior knowledge of the degradation model. We validate DIIP on various degradation-blind IR tasks, including JPEG artifact removal, waterdrop removal, denoising and super-resolution with state-of-the-art results.
Authors: Anis Ur Rahman, Einari Heinaro, Mete Ahishali, Samuli Junttila
Abstract: Mapping standing dead trees is critical for assessing forest health, monitoring biodiversity, and mitigating wildfire risks, for which aerial imagery has proven useful. However, dense canopy structures, spectral overlaps between living and dead vegetation, and over-segmentation errors limit the reliability of existing methods. This study introduces a hybrid postprocessing framework that refines deep learning-based tree segmentation by integrating watershed algorithms with adaptive filtering, enhancing boundary delineation, and reducing false positives in complex forest environments. Tested on high-resolution aerial imagery from boreal forests, the framework improved instance-level segmentation accuracy by 41.5% and reduced positional errors by 57%, demonstrating robust performance in densely vegetated regions. By balancing detection accuracy and over-segmentation artifacts, the method enabled the precise identification of individual dead trees, which is critical for ecological monitoring. The framework's computational efficiency supports scalable applications, such as wall-to-wall tree mortality mapping over large geographic regions using aerial or satellite imagery. These capabilities directly benefit wildfire risk assessment (identifying fuel accumulations), carbon stock estimation (tracking emissions from decaying biomass), and precision forestry (targeting salvage loggings). By bridging advanced remote sensing techniques with practical forest management needs, this work advances tools for large-scale ecological conservation and climate resilience planning.
Authors: Lucas Nunes, Rodrigo Marcuzzi, Jens Behley, Cyrill Stachniss
Abstract: Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the complexity of collecting and annotating 3D data is a bottleneck in this developments. To overcome that data annotation limitation, synthetic simulated data has been used to generate annotated data on demand. There is still however a domain gap between real and simulated data. More recently, diffusion models have been in the spotlight, enabling close-to-real data synthesis. Those generative models have been recently applied to the 3D data domain for generating scene-scale data with semantic annotations. Still, those methods either rely on image projection or decoupled models trained with different resolutions in a coarse-to-fine manner. Such intermediary representations impact the generated data quality due to errors added in those transformations. In this work, we propose a novel approach able to generate 3D semantic scene-scale data without relying on any projection or decoupled trained multi-resolution models, achieving more realistic semantic scene data generation compared to previous state-of-the-art methods. Besides improving 3D semantic scene-scale data synthesis, we thoroughly evaluate the use of the synthetic scene samples as labeled data to train a semantic segmentation network. In our experiments, we show that using the synthetic annotated data generated by our method as training data together with the real semantic segmentation labels, leads to an improvement in the semantic segmentation model performance. Our results show the potential of generated scene-scale point clouds to generate more training data to extend existing datasets, reducing the data annotation effort. Our code is available at https://github.com/PRBonn/3DiSS.
Authors: Xiaoqin Wang, Xusen Ma, Xianxu Hou, Meidan Ding, Yudong Li, Junliang Chen, Wenting Chen, Xiaoyang Peng, Linlin Shen
Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://github.com/CVI-SZU/FaceBench.
Authors: Chirag Parikh, Deepti Rawat, Rakshitha R. T., Tathagata Ghosh, Ravi Kiran Sarvadevabhatla
Abstract: We introduce RoadSocial, a large-scale, diverse VideoQA dataset tailored for generic road event understanding from social media narratives. Unlike existing datasets limited by regional bias, viewpoint bias and expert-driven annotations, RoadSocial captures the global complexity of road events with varied geographies, camera viewpoints (CCTV, handheld, drones) and rich social discourse. Our scalable semi-automatic annotation framework leverages Text LLMs and Video LLMs to generate comprehensive question-answer pairs across 12 challenging QA tasks, pushing the boundaries of road event understanding. RoadSocial is derived from social media videos spanning 14M frames and 414K social comments, resulting in a dataset with 13.2K videos, 674 tags and 260K high-quality QA pairs. We evaluate 18 Video LLMs (open-source and proprietary, driving-specific and general-purpose) on our road event understanding benchmark. We also demonstrate RoadSocial's utility in improving road event understanding capabilities of general-purpose Video LLMs.
Authors: Deependra Singh, Saksham Agarwal, Subhankar Mishra
Abstract: Our research is motivated by the urgent global issue of a large population affected by retinal diseases, which are evenly distributed but underserved by specialized medical expertise, particularly in non-urban areas. Our primary objective is to bridge this healthcare gap by developing a comprehensive diagnostic system capable of accurately predicting retinal diseases solely from fundus images. However, we faced significant challenges due to limited, diverse datasets and imbalanced class distributions. To overcome these issues, we have devised innovative strategies. Our research introduces novel approaches, utilizing hybrid models combining deeper Convolutional Neural Networks (CNNs), Transformer encoders, and ensemble architectures sequentially and in parallel to classify retinal fundus images into 20 disease labels. Our overarching goal is to assess these advanced models' potential in practical applications, with a strong focus on enhancing retinal disease diagnosis accuracy across a broader spectrum of conditions. Importantly, our efforts have surpassed baseline model results, with the C-Tran ensemble model emerging as the leader, achieving a remarkable model score of 0.9166, surpassing the baseline score of 0.9. Additionally, experiments with the IEViT model showcased equally promising outcomes with improved computational efficiency. We've also demonstrated the effectiveness of dynamic patch extraction and the integration of domain knowledge in computer vision tasks. In summary, our research strives to contribute significantly to retinal disease diagnosis, addressing the critical need for accessible healthcare solutions in underserved regions while aiming for comprehensive and accurate disease prediction.
Authors: Wenyi Xiong, Jian Chen, Ziheng Qi
Abstract: Trajectory prediction, as a critical component of autonomous driving systems, has attracted the attention of many researchers. Existing prediction algorithms focus on extracting more detailed scene features or selecting more reasonable trajectory destinations. However, in the face of dynamic and evolving future movements of the target vehicle, these algorithms cannot provide a fine-grained and continuous description of future behaviors and lane constraints, which degrades the prediction accuracy. To address this challenge, we present BLNet, a novel dualstream architecture that synergistically integrates behavioral intention recognition and lane constraint modeling through parallel attention mechanisms. The framework generates fine-grained behavior state queries (capturing spatial-temporal movement patterns) and lane queries (encoding lane topology constraints), supervised by two auxiliary losses, respectively. Subsequently, a two-stage decoder first produces trajectory proposals, then performs point-level refinement by jointly incorporating both the continuity of passed lanes and future motion features. Extensive experiments on two large datasets, nuScenes and Argoverse, show that our network exhibits significant performance gains over existing direct regression and goal-based algorithms.
Authors: Shuming Liu, Chen Zhao, Tianqi Xu, Bernard Ghanem
Abstract: Large video-language models (VLMs) have demonstrated promising progress in various video understanding tasks. However, their effectiveness in long-form video analysis is constrained by limited context windows. Traditional approaches, such as uniform frame sampling, often inevitably allocate resources to irrelevant content, diminishing their effectiveness in real-world scenarios. In this paper, we introduce BOLT, a method to BOost Large VLMs without additional Training through a comprehensive study of frame selection strategies. First, to enable a more realistic evaluation of VLMs in long-form video understanding, we propose a multi-source retrieval evaluation setting. Our findings reveal that uniform sampling performs poorly in noisy contexts, underscoring the importance of selecting the right frames. Second, we explore several frame selection strategies based on query-frame similarity and analyze their effectiveness at inference time. Our results show that inverse transform sampling yields the most significant performance improvement, increasing accuracy on the Video-MME benchmark from 53.8% to 56.1% and MLVU benchmark from 58.9% to 63.4%. Our code is available at https://github.com/sming256/BOLT.
Authors: Hamadi Chihaoui, Paolo Favaro
Abstract: Two of the main challenges of image restoration in real-world scenarios are the accurate characterization of an image prior and the precise modeling of the image degradation operator. Pre-trained diffusion models have been very successfully used as image priors in zero-shot image restoration methods. However, how to best handle the degradation operator is still an open problem. In real-world data, methods that rely on specific parametric assumptions about the degradation model often face limitations in their applicability. To address this, we introduce Invert2Restore, a zero-shot, training-free method that operates in both fully blind and partially blind settings -- requiring no prior knowledge of the degradation model or only partial knowledge of its parametric form without known parameters. Despite this, Invert2Restore achieves high-fidelity results and generalizes well across various types of image degradation. It leverages a pre-trained diffusion model as a deterministic mapping between normal samples and undistorted image samples. The key insight is that the input noise mapped by a diffusion model to a degraded image lies in a low-probability density region of the standard normal distribution. Thus, we can restore the degraded image by carefully guiding its input noise toward a higher-density region. We experimentally validate Invert2Restore across several image restoration tasks, demonstrating that it achieves state-of-the-art performance in scenarios where the degradation operator is either unknown or partially known.
Authors: Edwin Tay, Nazli T\"umer, Amir A. Zadpoor
Abstract: Living biological tissue is a complex system, constantly growing and changing in response to external and internal stimuli. These processes lead to remarkable and intricate changes in shape. Modeling and understanding both natural and pathological (or abnormal) changes in the shape of anatomical structures is highly relevant, with applications in diagnostic, prognostic, and therapeutic healthcare. Nevertheless, modeling the longitudinal shape change of biological tissue is a non-trivial task due to its inherent nonlinear nature. In this review, we highlight several existing methodologies and tools for modeling longitudinal shape change (i.e., spatiotemporal shape modeling). These methods range from diffeomorphic metric mapping to deep-learning based approaches (e.g., autoencoders, generative networks, recurrent neural networks, etc.). We discuss the synergistic combinations of existing technologies and potential directions for future research, underscoring key deficiencies in the current research landscape.
Authors: Yuxi Hu, Jun Zhang, Zhe Zhang, Rafael Weilharter, Yuchen Rao, Kuangyi Chen, Runze Yuan, Friedrich Fraundorfer
Abstract: Multi-view Stereo (MVS) aims to estimate depth and reconstruct 3D point clouds from a series of overlapping images. Recent learning-based MVS frameworks overlook the geometric information embedded in features and correlations, leading to weak cost matching. In this paper, we propose ICG-MVSNet, which explicitly integrates intra-view and cross-view relationships for depth estimation. Specifically, we develop an intra-view feature fusion module that leverages the feature coordinate correlations within a single image to enhance robust cost matching. Additionally, we introduce a lightweight cross-view aggregation module that efficiently utilizes the contextual information from volume correlations to guide regularization. Our method is evaluated on the DTU dataset and Tanks and Temples benchmark, consistently achieving competitive performance against state-of-the-art works, while requiring lower computational resources.
Authors: Achint Soni, Meet Soni, Sirisha Rambhatla
Abstract: Text-guided image editing aims to modify specific regions of an image according to natural language instructions while maintaining the general structure and the background fidelity. Existing methods utilize masks derived from cross-attention maps generated from diffusion models to identify the target regions for modification. However, since cross-attention mechanisms focus on semantic relevance, they struggle to maintain the image integrity. As a result, these methods often lack spatial consistency, leading to editing artifacts and distortions. In this work, we address these limitations and introduce LOCATEdit, which enhances cross-attention maps through a graph-based approach utilizing self-attention-derived patch relationships to maintain smooth, coherent attention across image regions, ensuring that alterations are limited to the designated items while retaining the surrounding structure. \method consistently and substantially outperforms existing baselines on PIE-Bench, demonstrating its state-of-the-art performance and effectiveness on various editing tasks. Code can be found on https://github.com/LOCATEdit/LOCATEdit/
Authors: Jonathan Lee, Bolivar Solarte, Chin-Hsuan Wu, Jin-Cheng Jhang, Fu-En Wang, Yi-Hsuan Tsai, Min Sun
Abstract: We present uLayout, a unified model for estimating room layout geometries from both perspective and panoramic images, whereas traditional solutions require different model designs for each image type. The key idea of our solution is to unify both domains into the equirectangular projection, particularly, allocating perspective images into the most suitable latitude coordinate to effectively exploit both domains seamlessly. To address the Field-of-View (FoV) difference between the input domains, we design uLayout with a shared feature extractor with an extra 1D-Convolution layer to condition each domain input differently. This conditioning allows us to efficiently formulate a column-wise feature regression problem regardless of the FoV input. This simple yet effective approach achieves competitive performance with current state-of-the-art solutions and shows for the first time a single end-to-end model for both domains. Extensive experiments in the real-world datasets, LSUN, Matterport3D, PanoContext, and Stanford 2D-3D evidence the contribution of our approach. Code is available at https://github.com/JonathanLee112/uLayout.
Authors: Tongchao Luo, Mingquan Qiu, Zhenyu Wu, Zebo Zhao, Dingyou Zhang
Abstract: To address the challenges of low diagnostic accuracy in traditional bearing fault diagnosis methods, this paper proposes a novel fault diagnosis approach based on multi-scale spectrum feature images and deep learning. Firstly, the vibration signal are preprocessed through mean removal and then converted to multi-length spectrum with fast Fourier transforms (FFT). Secondly, a novel feature called multi-scale spectral image (MSSI) is constructed by multi-length spectrum paving scheme. Finally, a deep learning framework, convolutional neural network (CNN), is formulated to diagnose the bearing faults. Two experimental cases are utilized to verify the effectiveness of the proposed method. Experimental results demonstrate that the proposed method significantly improves the accuracy of fault diagnosis.
Authors: Liuyue Xie, Jiancong Guo, Ozan Cakmakci, Andre Araujo, Laszlo A. Jeni, Zhiheng Jia
Abstract: Accurate camera calibration is a fundamental task for 3D perception, especially when dealing with real-world, in-the-wild environments where complex optical distortions are common. Existing methods often rely on pre-rectified images or calibration patterns, which limits their applicability and flexibility. In this work, we introduce a novel framework that addresses these challenges by jointly modeling camera intrinsic and extrinsic parameters using a generic ray camera model. Unlike previous approaches, AlignDiff shifts focus from semantic to geometric features, enabling more accurate modeling of local distortions. We propose AlignDiff, a diffusion model conditioned on geometric priors, enabling the simultaneous estimation of camera distortions and scene geometry. To enhance distortion prediction, we incorporate edge-aware attention, focusing the model on geometric features around image edges, rather than semantic content. Furthermore, to enhance generalizability to real-world captures, we incorporate a large database of ray-traced lenses containing over three thousand samples. This database characterizes the distortion inherent in a diverse variety of lens forms. Our experiments demonstrate that the proposed method significantly reduces the angular error of estimated ray bundles by ~8.2 degrees and overall calibration accuracy, outperforming existing approaches on challenging, real-world datasets.
Authors: Jincheng Yan, Yun Wang, Xiaoyan Luo, Yu-Wing Tai
Abstract: Person re-identification (ReID) plays a critical role in applications like security surveillance and criminal investigations by matching individuals across large image galleries captured by non-overlapping cameras. Traditional ReID methods rely on unimodal inputs, typically images, but face limitations due to challenges like occlusions, lighting changes, and pose variations. While advancements in image-based and text-based ReID systems have been made, the integration of both modalities has remained under-explored. This paper presents FusionSegReID, a multimodal model that combines both image and text inputs for enhanced ReID performance. By leveraging the complementary strengths of these modalities, our model improves matching accuracy and robustness, particularly in complex, real-world scenarios where one modality may struggle. Our experiments show significant improvements in Top-1 accuracy and mean Average Precision (mAP) for ReID, as well as better segmentation results in challenging scenarios like occlusion and low-quality images. Ablation studies further confirm that multimodal fusion and segmentation modules contribute to enhanced re-identification and mask accuracy. The results show that FusionSegReID outperforms traditional unimodal models, offering a more robust and flexible solution for real-world person ReID tasks.
Authors: Jiahui Chen, Yang Huan, Runhua Shi, Chanfan Ding, Xiaoqi Mo, Siyu Xiong, Yinong He
Abstract: Gestures are essential for enhancing co-speech communication, offering visual emphasis and complementing verbal interactions. While prior work has concentrated on point-level motion or fully supervised data-driven methods, we focus on co-speech gestures, advocating for weakly supervised learning and pixel-level motion deviations. We introduce a weakly supervised framework that learns latent representation deviations, tailored for co-speech gesture video generation. Our approach employs a diffusion model to integrate latent motion features, enabling more precise and nuanced gesture representation. By leveraging weakly supervised deviations in latent space, we effectively generate hand gestures and mouth movements, crucial for realistic video production. Experiments show our method significantly improves video quality, surpassing current state-of-the-art techniques.
Authors: Lars Heckler-Kram, Jan-Hendrik Neudeck, Ulla Scheler, Rebecca K\"onig, Carsten Steger
Abstract: In recent years, performance on existing anomaly detection benchmarks like MVTec AD and VisA has started to saturate in terms of segmentation AU-PRO, with state-of-the-art models often competing in the range of less than one percentage point. This lack of discriminatory power prevents a meaningful comparison of models and thus hinders progress of the field, especially when considering the inherent stochastic nature of machine learning results. We present MVTec AD 2, a collection of eight anomaly detection scenarios with more than 8000 high-resolution images. It comprises challenging and highly relevant industrial inspection use cases that have not been considered in previous datasets, including transparent and overlapping objects, dark-field and back light illumination, objects with high variance in the normal data, and extremely small defects. We provide comprehensive evaluations of state-of-the-art methods and show that their performance remains below 60% average AU-PRO. Additionally, our dataset provides test scenarios with lighting condition changes to assess the robustness of methods under real-world distribution shifts. We host a publicly accessible evaluation server that holds the pixel-precise ground truth of the test set (https://benchmark.mvtec.com/). All image data is available at https://www.mvtec.com/company/research/datasets/mvtec-ad-2.
URLs: https://benchmark.mvtec.com/)., https://www.mvtec.com/company/research/datasets/mvtec-ad-2.
Authors: Kuang Wu, Chuan Yang, Zhanbin Li
Abstract: Vectorized high-definition (HD) maps are essential for an autonomous driving system. Recently, state-of-the-art map vectorization methods are mainly based on DETR-like framework to generate HD maps in an end-to-end manner. In this paper, we propose InteractionMap, which improves previous map vectorization methods by fully leveraging local-to-global information interaction in both time and space. Firstly, we explore enhancing DETR-like detectors by explicit position relation prior from point-level to instance-level, since map elements contain strong shape priors. Secondly, we propose a key-frame-based hierarchical temporal fusion module, which interacts temporal information from local to global. Lastly, the separate classification branch and regression branch lead to the problem of misalignment in the output distribution. We interact semantic information with geometric information by introducing a novel geometric-aware classification loss in optimization and a geometric-aware matching cost in label assignment. InteractionMap achieves state-of-the-art performance on both nuScenes and Argoverse2 benchmarks.
Authors: Nikin~Matharaarachchi, Muhammad~Fermi Pasha, Sonya~Coleman, Kah PengWong
Abstract: Micro-expressions are short bursts of emotion that are difficult to hide. Their detection in children is an important cue to assist psychotherapists in conducting better therapy. However, existing research on the detection of micro-expressions has focused on adults, whose expressions differ in their characteristics from those of children. The lack of research is a direct consequence of the lack of a child-based micro-expressions dataset as it is much more challenging to capture children's facial expressions due to the lack of predictability and controllability. This study compiles a dataset of spontaneous child micro-expression videos, the first of its kind, to the best of the authors knowledge. The dataset is captured in the wild using video conferencing software. This dataset enables us to then explore key features and differences between adult and child micro-expressions. This study also establishes a baseline for the automated spotting and recognition of micro-expressions in children using three approaches comprising of hand-created and learning-based approaches.
Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif
Abstract: The integration of multi-view imaging and pose estimation represents a significant advance in computer vision applications, offering new possibilities for understanding human movement and interactions. This work presents a new algorithm that improves multi-view multi-person pose estimation, focusing on fast triangulation speeds and good generalization capabilities. The approach extends to whole-body pose estimation, capturing details from facial expressions to finger movements across multiple individuals and viewpoints. Adaptability to different settings is demonstrated through strong performance across unseen datasets and configurations. To support further progress in this field, all of this work is publicly accessible.
Authors: Jiahe Qian, Yaoyu Fang, Jinkui Hao, Bo Zhou
Abstract: Accurate segmentation of cell nuclei in histopathology images is essential for numerous biomedical research and clinical applications. However, existing cell nucleus segmentation methods only consider a single dataset (i.e., primary domain), while neglecting to leverage supplementary data from diverse sources (i.e., auxiliary domains) to reduce overfitting and enhance the performance. Although incorporating multiple datasets could alleviate overfitting, it often exacerbates performance drops caused by domain shifts. In this work, we introduce Adversarial Multi-domain Alignment of Segment Anything Model (AMA-SAM) that extends the Segment Anything Model (SAM) to overcome these obstacles through two key innovations. First, we propose a Conditional Gradient Reversal Layer (CGRL), a multi-domain alignment module that harmonizes features from diverse domains to promote domain-invariant representation learning while preserving crucial discriminative features for the primary dataset. Second, we address SAM's inherent low-resolution output by designing a High-Resolution Decoder (HR-Decoder), which directly produces fine-grained segmentation maps in order to capture intricate nuclei boundaries in high-resolution histology images. To the best of our knowledge, this is the first attempt to adapt SAM for multi-dataset learning with application to histology nuclei segmentation. We validate our method on several publicly available datasets, demonstrating consistent and significant improvements over state-of-the-art approaches.
Authors: Jaywon Koo, Jefferson Hernandez, Moayed Haji-Ali, Ziyan Yang, Vicente Ordonez
Abstract: Evaluating text-to-image synthesis is challenging due to misalignment between established metrics and human preferences. We propose cFreD, a metric based on the notion of Conditional Fr\'echet Distance that explicitly accounts for both visual fidelity and text-prompt alignment. Existing metrics such as Inception Score (IS), Fr\'echet Inception Distance (FID) and CLIPScore assess either image quality or image-text alignment but not both which limits their correlation with human preferences. Scoring models explicitly trained to replicate human preferences require constant updates and may not generalize to novel generation techniques or out-of-domain inputs. Through extensive experiments across multiple recently proposed text-to-image models and diverse prompt datasets, we demonstrate that cFreD exhibits a higher correlation with human judgments compared to statistical metrics, including metrics trained with human preferences. Our findings validate cFreD as a robust, future-proof metric for the systematic evaluation of text-to-image models, standardizing benchmarking in this rapidly evolving field. We release our evaluation toolkit and benchmark in the appendix.
Authors: Mallika Garg, Debashis Ghosh, Pyari Mohan Pradhan
Abstract: Occlusion is one of the challenging issues when estimating 3D hand pose. This problem becomes more prominent when hand interacts with an object or two hands are involved. In the past works, much attention has not been given to these occluded regions. But these regions contain important and beneficial information that is vital for 3D hand pose estimation. Thus, in this paper, we propose an occlusion robust and accurate method for the estimation of 3D hand-object pose from the input RGB image. Our method includes first localising the hand joints using a CNN based model and then refining them by extracting contextual information. The self attention transformer then identifies the specific joints along with the hand identity. This helps the model to identify the hand belongingness of a particular joint which helps to detect the joint even in the occluded region. Further, these joints with hand identity are then used to estimate the pose using cross attention mechanism. Thus, by identifying the joints in the occluded region, the obtained network becomes robust to occlusion. Hence, this network achieves state-of-the-art results when evaluated on the InterHand2.6M, HO3D and H$_2$O3D datasets.
Authors: Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, Yangguang Li
Abstract: Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. This paper introduces SparseFlex, a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $1024^3$ directly from rendering losses. SparseFlex combines the accuracy of Flexicubes with a sparse voxel structure, focusing computation on surface-adjacent regions and efficiently handling open surfaces. Crucially, we introduce a frustum-aware sectional voxel training strategy that activates only relevant voxels during rendering, dramatically reducing memory consumption and enabling high-resolution training. This also allows, for the first time, the reconstruction of mesh interiors using only rendering supervision. Building upon this, we demonstrate a complete shape modeling pipeline by training a variational autoencoder (VAE) and a rectified flow transformer for high-quality 3D shape generation. Our experiments show state-of-the-art reconstruction accuracy, with a ~82% reduction in Chamfer Distance and a ~88% increase in F-score compared to previous methods, and demonstrate the generation of high-resolution, detailed 3D shapes with arbitrary topology. By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.
Authors: Yuhan Zhang, Mengchen Zhang, Tong Wu, Tengfei Wang, Gordon Wetzstein, Dahua Lin, Ziwei Liu
Abstract: 3D generation is experiencing rapid advancements, while the development of 3D evaluation has not kept pace. How to keep automatic evaluation equitably aligned with human perception has become a well-recognized challenge. Recent advances in the field of language and image generation have explored human preferences and showcased respectable fitting ability. However, the 3D domain still lacks such a comprehensive preference dataset over generative models. To mitigate this absence, we develop 3DGen-Arena, an integrated platform in a battle manner. Then, we carefully design diverse text and image prompts and leverage the arena platform to gather human preferences from both public users and expert annotators, resulting in a large-scale multi-dimension human preference dataset 3DGen-Bench. Using this dataset, we further train a CLIP-based scoring model, 3DGen-Score, and a MLLM-based automatic evaluator, 3DGen-Eval. These two models innovatively unify the quality evaluation of text-to-3D and image-to-3D generation, and jointly form our automated evaluation system with their respective strengths. Extensive experiments demonstrate the efficacy of our scoring model in predicting human preferences, exhibiting a superior correlation with human ranks compared to existing metrics. We believe that our 3DGen-Bench dataset and automated evaluation system will foster a more equitable evaluation in the field of 3D generation, further promoting the development of 3D generative models and their downstream applications.
Authors: Aniket Didolkar, Andrii Zadaianchuk, Rabiul Awal, Maximilian Seitzer, Efstratios Gavves, Aishwarya Agrawal
Abstract: Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown remarkable success in object discovery in diverse domains, including complex real-world scenes. However, these models suffer from a key limitation: they lack controllability. Specifically, current object-centric models learn representations based on their preconceived understanding of objects, without allowing user input to guide which objects are represented. Introducing controllability into object-centric models could unlock a range of useful capabilities, such as the ability to extract instance-specific representations from a scene. In this work, we propose a novel approach for user-directed control over slot representations by conditioning slots on language descriptions. The proposed ConTRoLlable Object-centric representation learning approach, which we term CTRL-O, achieves targeted object-language binding in complex real-world scenes without requiring mask supervision. Next, we apply these controllable slot representations on two downstream vision language tasks: text-to-image generation and visual question answering. The proposed approach enables instance-specific text-to-image generation and also achieves strong performance on visual question answering.
Authors: Shitian Zhao, Qilong Wu, Xinyue Li, Bo Zhang, Ming Li, Qi Qin, Dongyang Liu, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Peng Gao, Bin Fu, Zhen Li
Abstract: We introduce LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity. Our approach follows a data-centric paradigm, constructing a high-quality data synthesis pipeline based on Deepseek-R1 to curate LeX-10K, a dataset of 10K high-resolution, aesthetically refined 1024$\times$1024 images. Beyond dataset construction, we develop LeX-Enhancer, a robust prompt enrichment model, and train two text-to-image models, LeX-FLUX and LeX-Lumina, achieving state-of-the-art text rendering performance. To systematically evaluate visual text generation, we introduce LeX-Bench, a benchmark that assesses fidelity, aesthetics, and alignment, complemented by Pairwise Normalized Edit Distance (PNED), a novel metric for robust text accuracy evaluation. Experiments demonstrate significant improvements, with LeX-Lumina achieving a 79.81% PNED gain on CreateBench, and LeX-FLUX outperforming baselines in color (+3.18%), positional (+4.45%), and font accuracy (+3.81%). Our codes, models, datasets, and demo are publicly available.
Authors: Yan Xia, Xiaowei Zhou, Etienne Vouga, Qixing Huang, Georgios Pavlakos
Abstract: In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that takes an image as input and estimates the parameters of the model. Due to the lack of training data for this task, we build a pipeline to produce pseudo ground truth model parameters for single images and implement a training procedure that iteratively refines these pseudo labels. Compared to state-of-the-art methods for 3D human mesh recovery, our model achieves competitive performance on standard benchmarks, while it significantly outperforms them in settings with extreme 3D poses and viewpoints. Additionally, we show that previous reconstruction methods frequently violate joint angle limits, leading to unnatural rotations. In contrast, our approach leverages the biomechanically plausible degrees of freedom making more realistic joint rotation estimates. We validate our approach across multiple human pose estimation benchmarks. We make the code, models and data available at: https://isshikihugh.github.io/HSMR/
Authors: Dian Zheng, Ziqi Huang, Hongbo Liu, Kai Zou, Yinan He, Fan Zhang, Yuanhan Zhang, Jingwen He, Wei-Shi Zheng, Yu Qiao, Ziwei Liu
Abstract: Video generation has advanced significantly, evolving from producing unrealistic outputs to generating videos that appear visually convincing and temporally coherent. To evaluate these video generative models, benchmarks such as VBench have been developed to assess their faithfulness, measuring factors like per-frame aesthetics, temporal consistency, and basic prompt adherence. However, these aspects mainly represent superficial faithfulness, which focus on whether the video appears visually convincing rather than whether it adheres to real-world principles. While recent models perform increasingly well on these metrics, they still struggle to generate videos that are not just visually plausible but fundamentally realistic. To achieve real "world models" through video generation, the next frontier lies in intrinsic faithfulness to ensure that generated videos adhere to physical laws, commonsense reasoning, anatomical correctness, and compositional integrity. Achieving this level of realism is essential for applications such as AI-assisted filmmaking and simulated world modeling. To bridge this gap, we introduce VBench-2.0, a next-generation benchmark designed to automatically evaluate video generative models for their intrinsic faithfulness. VBench-2.0 assesses five key dimensions: Human Fidelity, Controllability, Creativity, Physics, and Commonsense, each further broken down into fine-grained capabilities. Tailored for individual dimensions, our evaluation framework integrates generalists such as state-of-the-art VLMs and LLMs, and specialists, including anomaly detection methods proposed for video generation. We conduct extensive annotations to ensure alignment with human judgment. By pushing beyond superficial faithfulness toward intrinsic faithfulness, VBench-2.0 aims to set a new standard for the next generation of video generative models in pursuit of intrinsic faithfulness.
Authors: Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos
Abstract: In this work, we aim to compress the vision tokens of a Large Vision Language Model (LVLM) into a representation that is simultaneously suitable for (a) generative and (b) discriminative tasks, (c) is nearly lossless, and (d) is storage-efficient. We propose a novel compression approach, called Fwd2Bot, that uses the LVLM itself to compress the visual information in a task-agnostic manner. At the core of Fwd2bot there exists a "double-forward pass" training strategy, whereby, during the first forward pass, the LLM (of the LVLM) creates a bottleneck by condensing the visual information into a small number of summary tokens. Then, using the same LLM, the second forward pass processes the language instruction(s) alongside the summary tokens, used as a direct replacement for the image ones. The training signal is provided by two losses: an autoregressive one applied after the second pass that provides a direct optimization objective for compression, and a contrastive loss, applied after the first pass, that further boosts the representation strength, especially for discriminative tasks. The training is further enhanced by stage-specific adapters. We accompany the proposed method by an in-depth ablation study. Overall, Fwd2Bot results in highly-informative compressed representations suitable for both generative and discriminative tasks. For generative tasks, we offer a 2x higher compression rate without compromising the generative capabilities, setting a new state-of-the-art result. For discriminative tasks, we set a new state-of-the-art on image retrieval and compositionality.
Authors: Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, Xiangyang Zhu, Manyuan Zhang, Will Beddow, Erwann Millon, Victor Perez, Wenhai Wang, Conghui He, Bo Zhang, Xiaohong Liu, Hongsheng Li, Yu Qiao, Chang Xu, Peng Gao
Abstract: We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a unified architecture (Unified Next-DiT) that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and allowing seamless task expansion. Besides, since high-quality captioners can provide semantically well-aligned text-image training pairs, we introduce a unified captioning system, Unified Captioner (UniCap), specifically designed for T2I generation tasks. UniCap excels at generating comprehensive and accurate captions, accelerating convergence and enhancing prompt adherence. (2) Efficiency - to improve the efficiency of our proposed model, we develop multi-stage progressive training strategies and introduce inference acceleration techniques without compromising image quality. Extensive evaluations on academic benchmarks and public text-to-image arenas show that Lumina-Image 2.0 delivers strong performances even with only 2.6B parameters, highlighting its scalability and design efficiency. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-Image-2.0.
Authors: David Yifan Yao, Albert J. Zhai, Shenlong Wang
Abstract: This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding.
Authors: Minghui Lin, Xiang Wang, Yishan Wang, Shu Wang, Fengqi Dai, Pengxiang Ding, Cunxiang Wang, Zhengrong Zuo, Nong Sang, Siteng Huang, Donglin Wang
Abstract: Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention - generated content often violates the fundamental laws of physics, falling into the dilemma of ''visual realism but physical absurdity". Researchers began to increasingly recognize the importance of physical fidelity in video generation and attempted to integrate heuristic physical cognition such as motion representations and physical knowledge into generative systems to simulate real-world dynamic scenarios. Considering the lack of a systematic overview in this field, this survey aims to provide a comprehensive summary of architecture designs and their applications to fill this gap. Specifically, we discuss and organize the evolutionary process of physical cognition in video generation from a cognitive science perspective, while proposing a three-tier taxonomy: 1) basic schema perception for generation, 2) passive cognition of physical knowledge for generation, and 3) active cognition for world simulation, encompassing state-of-the-art methods, classical paradigms, and benchmarks. Subsequently, we emphasize the inherent key challenges in this domain and delineate potential pathways for future research, contributing to advancing the frontiers of discussion in both academia and industry. Through structured review and interdisciplinary analysis, this survey aims to provide directional guidance for developing interpretable, controllable, and physically consistent video generation paradigms, thereby propelling generative models from the stage of ''visual mimicry'' towards a new phase of ''human-like physical comprehension''.
Authors: Haolin Liu, Xiaohang Zhan, Zizheng Yan, Zhongjin Luo, Yuxin Wen, Xiaoguang Han
Abstract: Establishing character shape correspondence is a critical and fundamental task in computer vision and graphics, with diverse applications including re-topology, attribute transfer, and shape interpolation. Current dominant functional map methods, while effective in controlled scenarios, struggle in real situations with more complex challenges such as non-isometric shape discrepancies. In response, we revisit registration-for-correspondence methods and tap their potential for more stable shape correspondence estimation. To overcome their common issues including unstable deformations and the necessity for careful pre-alignment or high-quality initial 3D correspondences, we introduce Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence. We first re-purpose a foundation model for 2D character correspondence that ensures reliable and stable 2D mappings. Crucially, we propose a novel Semantic Flow Guided Registration approach that leverages 2D correspondence to guide mesh deformations. Our framework significantly surpasses existing methods in challenging scenarios, and brings possibilities for a wide array of real applications, as demonstrated in our results.
Authors: Hairong Yin, Huangying Zhan, Yi Xu, Raymond A. Yeh
Abstract: Open-vocabulary querying in 3D Gaussian Splatting aims to identify semantically relevant regions within a 3D Gaussian representation based on a given text query. Prior work, such as LangSplat, addressed this task by retrieving these regions in the form of segmentation masks on 2D renderings. More recently, OpenGaussian introduced point-level querying, which directly selects a subset of 3D Gaussians. In this work, we propose a point-level querying method that builds upon LangSplat's framework. Our approach improves the framework in two key ways: (a) we leverage masklets from the Segment Anything Model 2 (SAM2) to establish semantic consistent ground-truth for distilling the language Gaussians; (b) we introduces a novel two-step querying approach that first retrieves the distilled ground-truth and subsequently uses the ground-truth to query the individual Gaussians. Experimental evaluations on three benchmark datasets demonstrate that the proposed method achieves better performance compared to state-of-the-art approaches. For instance, our method achieves an mIoU improvement of +20.42 on the 3D-OVS dataset.
Authors: Anand Bhattad, Konpat Preechakul, Alexei A. Efros
Abstract: This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a single image until only the background remains. Just as Jenga players must understand structural dependencies to maintain tower stability, our task reveals the intrinsic relationships between scene elements by systematically exploring which objects can be removed while preserving scene coherence in both physical and geometric sense. As a starting point for tackling the Visual Jenga task, we propose a simple, data-driven, training-free approach that is surprisingly effective on a range of real-world images. The principle behind our approach is to utilize the asymmetry in the pairwise relationships between objects within a scene and employ a large inpainting model to generate a set of counterfactuals to quantify the asymmetry.
Authors: Hongkai Lin, Dingkang Liang, Zhenghao Qi, Xiang Bai
Abstract: Underwater dense prediction, especially depth estimation and semantic segmentation, is crucial for gaining a comprehensive understanding of underwater scenes. Nevertheless, high-quality and large-scale underwater datasets with dense annotations remain scarce because of the complex environment and the exorbitant data collection costs. This paper proposes a unified Text-to-Image and DEnse annotation generation method (TIDE) for underwater scenes. It relies solely on text as input to simultaneously generate realistic underwater images and multiple highly consistent dense annotations. Specifically, we unify the generation of text-to-image and text-to-dense annotations within a single model. The Implicit Layout Sharing mechanism (ILS) and cross-modal interaction method called Time Adaptive Normalization (TAN) are introduced to jointly optimize the consistency between image and dense annotations. We synthesize a large-scale underwater dataset using TIDE to validate the effectiveness of our method in underwater dense prediction tasks. The results demonstrate that our method effectively improves the performance of existing underwater dense prediction models and mitigates the scarcity of underwater data with dense annotations. We hope our method can offer new perspectives on alleviating data scarcity issues in other fields. The code is available at https: //github.com/HongkLin/TIDE.
Authors: Zilin Xiao, Pavel Suma, Ayush Sachdeva, Hao-Jen Wang, Giorgos Kordopatis-Zilos, Giorgos Tolias, Vicente Ordonez
Abstract: We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is used for image retrieval, where typically a first ranking is performed with an efficient similarity measure, and then a shortlist of top-ranked images is re-ranked based on a more fine-grained similarity measure. Compared to existing methods that perform pair-wise similarity estimation with local descriptors or list-wise re-ranking with global descriptors, LOCORE is the first method to perform list-wise re-ranking with local descriptors. To achieve this, we leverage efficient long-context sequence models to effectively capture the dependencies between query and gallery images at the local-descriptor level. During testing, we process long shortlists with a sliding window strategy that is tailored to overcome the context size limitations of sequence models. Our approach achieves superior performance compared with other re-rankers on established image retrieval benchmarks of landmarks (ROxf and RPar), products (SOP), fashion items (In-Shop), and bird species (CUB-200) while having comparable latency to the pair-wise local descriptor re-rankers.
Authors: Jianning Pei, Han Hu, Shuyang Gu
Abstract: Diffusion models achieve remarkable generation quality but suffer from computational intensive sampling due to suboptimal step discretization. While existing works focus on optimizing denoising directions, we address the principled design of stepsize schedules. This paper proposes Optimal Stepsize Distillation, a dynamic programming framework that extracts theoretically optimal schedules by distilling knowledge from reference trajectories. By reformulating stepsize optimization as recursive error minimization, our method guarantees global discretization bounds through optimal substructure exploitation. Crucially, the distilled schedules demonstrate strong robustness across architectures, ODE solvers, and noise schedules. Experiments show 10x accelerated text-to-image generation while preserving 99.4% performance on GenEval. Our code is available at https://github.com/bebebe666/OptimalSteps.
Authors: Ziyu Guo, Young Yoon Lee, Joseph Liu, Yizhak Ben-Shabat, Victor Zordan, Mubbasir Kapadia
Abstract: We present StyleMotif, a novel Stylized Motion Latent Diffusion model, generating motion conditioned on both content and style from multiple modalities. Unlike existing approaches that either focus on generating diverse motion content or transferring style from sequences, StyleMotif seamlessly synthesizes motion across a wide range of content while incorporating stylistic cues from multi-modal inputs, including motion, text, image, video, and audio. To achieve this, we introduce a style-content cross fusion mechanism and align a style encoder with a pre-trained multi-modal model, ensuring that the generated motion accurately captures the reference style while preserving realism. Extensive experiments demonstrate that our framework surpasses existing methods in stylized motion generation and exhibits emergent capabilities for multi-modal motion stylization, enabling more nuanced motion synthesis. Source code and pre-trained models will be released upon acceptance. Project Page: https://stylemotif.github.io
Authors: Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Benyou Wang, Xiangyu Yue
Abstract: Inspired by DeepSeek-R1's success in eliciting reasoning abilities through rule-based reinforcement learning (RL), we introduce Video-R1 as the first attempt to systematically explore the R1 paradigm for eliciting video reasoning within multimodal large language models (MLLMs). However, directly applying RL training with the GRPO algorithm to video reasoning presents two primary challenges: (i) a lack of temporal modeling for video reasoning, and (ii) the scarcity of high-quality video-reasoning data. To address these issues, we first propose the T-GRPO algorithm, which encourages models to utilize temporal information in videos for reasoning. Additionally, instead of relying solely on video data, we incorporate high-quality image-reasoning data into the training process. We have constructed two datasets: Video-R1-COT-165k for SFT cold start and Video-R1-260k for RL training, both comprising image and video data. Experimental results demonstrate that Video-R1 achieves significant improvements on video reasoning benchmarks such as VideoMMMU and VSI-Bench, as well as on general video benchmarks including MVBench and TempCompass, etc. Notably, Video-R1-7B attains a 35.8% accuracy on video spatial reasoning benchmark VSI-bench, surpassing the commercial proprietary model GPT-4o. All codes, models, data are released.
Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Abstract: Visual in-context learning (VICL), as a new paradigm in computer vision, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. While effective, the existing VICL paradigm exhibits poor generalizability under distribution shifts. In this work, we propose test-time Visual In-Context Tuning (VICT), a method that can adapt VICL models on the fly with a single test sample. Specifically, we flip the role between the task prompts and the test sample and use a cycle consistency loss to reconstruct the original task prompt output. Our key insight is that a model should be aware of a new test distribution if it can successfully recover the original task prompts. Extensive experiments on six representative vision tasks ranging from high-level visual understanding to low-level image processing, with 15 common corruptions, demonstrate that our VICT can improve the generalizability of VICL to unseen new domains. In addition, we show the potential of applying VICT for unseen tasks at test time. Code: https://github.com/Jiahao000/VICT.
Authors: Ziren Gong, Fabio Tosi, Youmin Zhang, Stefano Mattoccia, Matteo Poggi
Abstract: NeRF-based SLAM has recently achieved promising results in tracking and reconstruction. However, existing methods face challenges in providing sufficient scene representation, capturing structural information, and maintaining global consistency in scenes emerging significant movement or being forgotten. To this end, we present HS-SLAM to tackle these problems. To enhance scene representation capacity, we propose a hybrid encoding network that combines the complementary strengths of hash-grid, tri-planes, and one-blob, improving the completeness and smoothness of reconstruction. Additionally, we introduce structural supervision by sampling patches of non-local pixels rather than individual rays to better capture the scene structure. To ensure global consistency, we implement an active global bundle adjustment (BA) to eliminate camera drifts and mitigate accumulative errors. Experimental results demonstrate that HS-SLAM outperforms the baselines in tracking and reconstruction accuracy while maintaining the efficiency required for robotics.
Authors: Weihao Yu, Yuanhao Cai, Ruyi Zha, Zhiwen Fan, Chenxin Li, Yixuan Yuan
Abstract: Four-dimensional computed tomography (4D CT) reconstruction is crucial for capturing dynamic anatomical changes but faces inherent limitations from conventional phase-binning workflows. Current methods discretize temporal resolution into fixed phases with respiratory gating devices, introducing motion misalignment and restricting clinical practicality. In this paper, We propose X$^2$-Gaussian, a novel framework that enables continuous-time 4D-CT reconstruction by integrating dynamic radiative Gaussian splatting with self-supervised respiratory motion learning. Our approach models anatomical dynamics through a spatiotemporal encoder-decoder architecture that predicts time-varying Gaussian deformations, eliminating phase discretization. To remove dependency on external gating devices, we introduce a physiology-driven periodic consistency loss that learns patient-specific breathing cycles directly from projections via differentiable optimization. Extensive experiments demonstrate state-of-the-art performance, achieving a 9.93 dB PSNR gain over traditional methods and 2.25 dB improvement against prior Gaussian splatting techniques. By unifying continuous motion modeling with hardware-free period learning, X$^2$-Gaussian advances high-fidelity 4D CT reconstruction for dynamic clinical imaging. Project website at: https://x2-gaussian.github.io/.
Authors: Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos, Marc Botet Colomer, Linus H\"arenstam-Nielsen, Mattia Segu, Pier Luigi Dovesi, Jussi Karlgren, Daniel Cremers, Federico Tombari, Matteo Poggi
Abstract: Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning for effective real-world applications. We introduce Semantic Library Adaptation (SemLA), a novel framework for training-free, test-time domain adaptation. SemLA leverages a library of LoRA-based adapters indexed with CLIP embeddings, dynamically merging the most relevant adapters based on proximity to the target domain in the embedding space. This approach constructs an ad-hoc model tailored to each specific input without additional training. Our method scales efficiently, enhances explainability by tracking adapter contributions, and inherently protects data privacy, making it ideal for sensitive applications. Comprehensive experiments on a 20-domain benchmark built over 10 standard datasets demonstrate SemLA's superior adaptability and performance across diverse settings, establishing a new standard in domain adaptation for open-vocabulary semantic segmentation.
Authors: Chi-Pin Huang, Yen-Siang Wu, Hung-Kai Chung, Kai-Po Chang, Fu-En Yang, Yu-Chiang Frank Wang
Abstract: Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions.
Authors: Abdelrahman Shaker, Muhammad Maaz, Chenhui Gou, Hamid Rezatofighi, Salman Khan, Fahad Shahbaz Khan
Abstract: Video understanding models often struggle with high computational requirements, extensive parameter counts, and slow inference speed, making them inefficient for practical use. To tackle these challenges, we propose Mobile-VideoGPT, an efficient multimodal framework designed to operate with fewer than a billion parameters. Unlike traditional video large multimodal models (LMMs), Mobile-VideoGPT consists of lightweight dual visual encoders, efficient projectors, and a small language model (SLM), enabling real-time throughput. To further improve efficiency, we present an Attention-Based Frame Scoring mechanism to select the key-frames, along with an efficient token projector that prunes redundant visual tokens and preserves essential contextual cues. We evaluate our model across well-established six video understanding benchmarks (e.g., MVBench, EgoSchema, NextQA, and PercepTest). Our results show that Mobile-VideoGPT-0.5B can generate up to 46 tokens per second while outperforming existing state-of-the-art 0.5B-parameter models by 6 points on average with 40% fewer parameters and more than 2x higher throughput. Our code and models are publicly available at: https://github.com/Amshaker/Mobile-VideoGPT.
Authors: Xiaoming Qi, Jingyang Zhang, Huazhu Fu, Guanyu Yang, Shuo Li, Yueming Jin
Abstract: Federated continual learning (FCL) offers an emerging pattern to facilitate the applicability of federated learning (FL) in real-world scenarios, where tasks evolve dynamically and asynchronously across clients, especially in medical scenario. Existing server-side FCL methods in nature domain construct a continually learnable server model by client aggregation on all-involved tasks. However, they are challenged by: (1) Catastrophic forgetting for previously learned tasks, leading to error accumulation in server model, making it difficult to sustain comprehensive knowledge across all tasks. (2) Biased optimization due to asynchronous tasks handled across different clients, leading to the collision of optimization targets of different clients at the same time steps. In this work, we take the first step to propose a novel server-side FCL pattern in medical domain, Dynamic Allocation Hypernetwork with adaptive model recalibration (FedDAH). It is to facilitate collaborative learning under the distinct and dynamic task streams across clients. To alleviate the catastrophic forgetting, we propose a dynamic allocation hypernetwork (DAHyper) where a continually updated hypernetwork is designed to manage the mapping between task identities and their associated model parameters, enabling the dynamic allocation of the model across clients. For the biased optimization, we introduce a novel adaptive model recalibration (AMR) to incorporate the candidate changes of historical models into current server updates, and assign weights to identical tasks across different time steps based on the similarity for continual optimization. Extensive experiments on the AMOS dataset demonstrate the superiority of our FedDAH to other FCL methods on sites with different task streams. The code is available:https://github.com/jinlab-imvr/FedDAH.
Authors: Viktor Schlegel, Anil A Bharath, Zilong Zhao, Kevin Yee
Abstract: Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or institutional reasons. This survey provides a comprehensive framework for understanding the landscape of privacy-preserving synthetic data, presenting the theoretical foundations of generative models and differential privacy followed by a review of state-of-the-art methods across tabular data, images, and text. Our synthesis of evaluation approaches highlights the fundamental trade-off between utility for down-stream tasks and privacy guarantees, while identifying critical research gaps: the lack of realistic benchmarks representing specialized domains and insufficient empirical evaluations required to contextualise formal guarantees. Through empirical analysis of four leading methods on five real-world datasets from specialized domains, we demonstrate significant performance degradation under realistic privacy constraints ($\epsilon \leq 4$), revealing a substantial gap between results reported on general domain benchmarks and performance on domain-specific data. %Our findings highlight key challenges including unaccounted privacy leakage, insufficient empirical verification of formal guarantees, and a critical deficit of realistic benchmarks. These challenges underscore the need for robust evaluation frameworks, standardized benchmarks for specialized domains, and improved techniques to address the unique requirements of privacy-sensitive fields such that this technology can deliver on its considerable potential.
Authors: Youngkyoon Jang, Eduardo P\'erez-Pellitero
Abstract: We propose Covisibility Map-based Gaussian Splatting (CoMapGS), designed to recover underrepresented sparse regions in sparse novel view synthesis. CoMapGS addresses both high- and low-uncertainty regions by constructing covisibility maps, enhancing initial point clouds, and applying uncertainty-aware weighted supervision using a proximity classifier. Our contributions are threefold: (1) CoMapGS reframes novel view synthesis by leveraging covisibility maps as a core component to address region-specific uncertainty; (2) Enhanced initial point clouds for both low- and high-uncertainty regions compensate for sparse COLMAP-derived point clouds, improving reconstruction quality and benefiting few-shot 3DGS methods; (3) Adaptive supervision with covisibility-score-based weighting and proximity classification achieves consistent performance gains across scenes with varying sparsity scores derived from covisibility maps. Experimental results demonstrate that CoMapGS outperforms state-of-the-art methods on datasets including Mip-NeRF 360 and LLFF.
Authors: Yiqing Shen, Chenjia Li, Bohan Liu, Cheng-Yi Li, Tito Porras, Mathias Unberath
Abstract: Analyzing operating room (OR) workflows to derive quantitative insights into OR efficiency is important for hospitals to maximize patient care and financial sustainability. Prior work on OR-level workflow analysis has relied on end-to-end deep neural networks. While these approaches work well in constrained settings, they are limited to the conditions specified at development time and do not offer the flexibility necessary to accommodate the OR workflow analysis needs of various OR scenarios (e.g., large academic center vs. rural provider) without data collection, annotation, and retraining. Reasoning segmentation (RS) based on foundation models offers this flexibility by enabling automated analysis of OR workflows from OR video feeds given only an implicit text query related to the objects of interest. Due to the reliance on large language model (LLM) fine-tuning, current RS approaches struggle with reasoning about semantic/spatial relationships and show limited generalization to OR video due to variations in visual characteristics and domain-specific terminology. To address these limitations, we first propose a novel digital twin (DT) representation that preserves both semantic and spatial relationships between the various OR components. Then, building on this foundation, we propose ORDiRS (Operating Room Digital twin representation for Reasoning Segmentation), an LLM-tuning-free RS framework that reformulates RS into a "reason-retrieval-synthesize" paradigm. Finally, we present ORDiRS-Agent, an LLM-based agent that decomposes OR workflow analysis queries into manageable RS sub-queries and generates responses by combining detailed textual explanations with supporting visual evidence from RS. Experimental results on both an in-house and a public OR dataset demonstrate that our ORDiRS achieves a cIoU improvement of 6.12%-9.74% compared to the existing state-of-the-arts.
Authors: Haoming Xu, Shuxun Wang, Yanqiu Zhao, Yi Zhong, Ziyan Jiang, Ningyuan Zhao, Shumin Deng, Huajun Chen, Ningyu Zhang
Abstract: This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models. This task aims to selectively erase sensitive knowledge from large language models, avoiding both over-forgetting and under-forgetting issues. We propose an unlearning system that leverages Model Merging (specifically TIES-Merging), combining two specialized models into a more balanced unlearned model. Our system achieves competitive results, ranking second among 26 teams, with an online score of 0.944 for Task Aggregate and 0.487 for overall Aggregate. In this paper, we also conduct local experiments and perform a comprehensive analysis of the unlearning process, examining performance trajectories, loss dynamics, and weight perspectives, along with several supplementary experiments, to understand the effectiveness of our method. Furthermore, we analyze the shortcomings of our method and evaluation metrics, emphasizing that MIA scores and ROUGE-based metrics alone are insufficient to fully evaluate successful unlearning. Finally, we emphasize the need for more comprehensive evaluation methodologies and rethinking of unlearning objectives in future research. Code is available at https://github.com/zjunlp/unlearn/tree/main/semeval25.
URLs: https://github.com/zjunlp/unlearn/tree/main/semeval25.
Authors: Saelyne Yang, Anh Truong, Juho Kim, Dingzeyu Li
Abstract: Tutorial videos are a valuable resource for people looking to learn new tasks. People often learn these skills by viewing multiple tutorial videos to get an overall understanding of a task by looking at different approaches to achieve the task. However, navigating through multiple videos can be time-consuming and mentally demanding as these videos are scattered and not easy to skim. We propose VideoMix, a system that helps users gain a holistic understanding of a how-to task by aggregating information from multiple videos on the task. Insights from our formative study (N=12) reveal that learners value understanding potential outcomes, required materials, alternative methods, and important details shared by different videos. Powered by a Vision-Language Model pipeline, VideoMix extracts and organizes this information, presenting concise textual summaries alongside relevant video clips, enabling users to quickly digest and navigate the content. A comparative user study (N=12) demonstrated that VideoMix enabled participants to gain a more comprehensive understanding of tasks with greater efficiency than a baseline video interface, where videos are viewed independently. Our findings highlight the potential of a task-oriented, multi-video approach where videos are organized around a shared goal, offering an enhanced alternative to conventional video-based learning.
Authors: Hongxuan Tang, Hao Liu, Xinyan Xiao
Abstract: We introduce UGen, a unified autoregressive multimodal model that demonstrates strong performance across text processing, image understanding, and image generation tasks simultaneously. UGen converts both texts and images into discrete token sequences and utilizes a single transformer to generate them uniformly in an autoregressive manner. To address the challenges associated with unified multimodal learning, UGen is trained using a novel mechanism, namely progressive vocabulary learning. In this process, visual token IDs are incrementally activated and integrated into the training phase, ultimately enhancing the effectiveness of unified multimodal learning. Experiments on comprehensive text and image tasks show that UGen achieves a significant overall performance improvement of 13.3% compared to the vanilla unified autoregressive method, and it also delivers competitive results across all tasks against several task-specific models.
Authors: Bingyan Xie, Yongpeng Wu, Yuxuan Shi, Biqian Feng, Wenjun Zhang, Jihong Park, Tony Q. S. Quek
Abstract: Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework, abbreviated as WVSC, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC first encodes original video frames as semantic frames and then conducts video coding based on such compact representations, enabling the video coding in semantic level rather than pixel level. Moreover, to further reduce the communication overhead, a reference semantic frame is introduced to substitute motion vectors of each frame in common video coding methods. At the receiver, multi-frame compensation (MFC) is proposed to produce compensated current semantic frame with a multi-frame fusion attention module. With both the reference frame transmission and MFC, the bandwidth efficiency improves with satisfying video transmission performance. Experimental results verify the performance gain of WVSC over other DL-based methods e.g. DVSC about 1 dB and traditional schemes about 2 dB in terms of PSNR.
Authors: Bashar Tahir, Philipp Svoboda, Markus Rupp
Abstract: Integrated sensing and communication (ISAC) is envisioned be to one of the paradigms upon which next-generation mobile networks will be built, extending localization and tracking capabilities, as well as giving birth to environment-aware wireless access. A key aspect of sensing integration is parameter estimation, which involves extracting information about the surrounding environment, such as the direction, distance, and velocity of various objects within. This is typically of a high-dimensional nature, which leads to significant computational complexity, if performed jointly across multiple sensing dimensions, such as space, frequency, and time. Additionally, due to the incorporation of sensing on top of the data transmission, the time window available for sensing is likely to be short, resulting in an estimation problem where only a single snapshot is accessible. In this work, we propose PLAIN, a tensor-based estimation architecture that flexibly scales with multiple sensing dimensions and can handle high dimensionality, limited measurement time, and super-resolution requirements. It consists of three stages: a compression stage, where the high dimensional input is converted into lower dimensionality, without sacrificing resolution; a decoupled estimation stage, where the parameters across the different dimensions are estimated in parallel with low complexity; an input-based fusion stage, where the decoupled parameters are fused together to form a paired multidimensional estimate. We investigate the performance of the architecture for different configurations and compare it against practical sequential and joint estimation baselines, as well as theoretical bounds. Our results show that PLAIN, using tools from tensor algebra, subspace-based processing, and compressed sensing, can scale flexibly with dimensionality, while operating with low complexity and maintaining super-resolution.
Authors: Erik Wallin, Fredrik Kahl, Lars Hammarstrand
Abstract: Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic relationships between OOD samples and the in-distribution (ID) classes. We propose a framework for detecting and classifying OOD samples in a given class hierarchy. Specifically, we aim to predict OOD data to their correct internal nodes of the class hierarchy, whereas the known ID classes should be predicted as their corresponding leaf nodes. Our approach leverages the class hierarchy to create a probabilistic model and we implement this model by using networks trained for ID classification at multiple hierarchy depths. We conduct experiments on three datasets with predefined class hierarchies and show the effectiveness of our method. Our code is available at https://github.com/walline/prohoc.
Authors: Yongxu Wang, Xu Cao, Weiyun Yi, Zhaoxin Fan
Abstract: Simultaneous Localization and Mapping (SLAM) is a critical task in robotics, enabling systems to autonomously navigate and understand complex environments. Current SLAM approaches predominantly rely on geometric cues for mapping and localization, but they often fail to ensure semantic consistency, particularly in dynamic or densely populated scenes. To address this limitation, we introduce STAMICS, a novel method that integrates semantic information with 3D Gaussian representations to enhance both localization and mapping accuracy. STAMICS consists of three key components: a 3D Gaussian-based scene representation for high-fidelity reconstruction, a graph-based clustering technique that enforces temporal semantic consistency, and an open-vocabulary system that allows for the classification of unseen objects. Extensive experiments show that STAMICS significantly improves camera pose estimation and map quality, outperforming state-of-the-art methods while reducing reconstruction errors. Code will be public available.
Authors: Qiyu Dai, Xingyu Ni, Qianfan Shen, Wenzheng Chen, Baoquan Chen, Mengyu Chu
Abstract: We consider the problem of adding dynamic rain effects to in-the-wild scenes in a physically-correct manner. Recent advances in scene modeling have made significant progress, with NeRF and 3DGS techniques emerging as powerful tools for reconstructing complex scenes. However, while effective for novel view synthesis, these methods typically struggle with challenging scene editing tasks, such as physics-based rain simulation. In contrast, traditional physics-based simulations can generate realistic rain effects, such as raindrops and splashes, but they often rely on skilled artists to carefully set up high-fidelity scenes. This process lacks flexibility and scalability, limiting its applicability to broader, open-world environments. In this work, we introduce RainyGS, a novel approach that leverages the strengths of both physics-based modeling and 3DGS to generate photorealistic, dynamic rain effects in open-world scenes with physical accuracy. At the core of our method is the integration of physically-based raindrop and shallow water simulation techniques within the fast 3DGS rendering framework, enabling realistic and efficient simulations of raindrop behavior, splashes, and reflections. Our method supports synthesizing rain effects at over 30 fps, offering users flexible control over rain intensity -- from light drizzles to heavy downpours. We demonstrate that RainyGS performs effectively for both real-world outdoor scenes and large-scale driving scenarios, delivering more photorealistic and physically-accurate rain effects compared to state-of-the-art methods. Project page can be found at https://pku-vcl-geometry.github.io/RainyGS/
Authors: Felix Terhag, Philipp Knechtges, Achim Basermann, Anja Bach, Darius Gerlach, Jens Tank, Ra\'ul Tempone
Abstract: Cardiac real-time magnetic resonance imaging (MRI) is an emerging technology that images the heart at up to 50 frames per second, offering insight into the respiratory effects on the heartbeat. However, this method significantly increases the number of images that must be segmented to derive critical health indicators. Although neural networks perform well on inner slices, predictions on outer slices are often unreliable. This work proposes sparse Bayesian learning (SBL) to predict the ventricular volume on outer slices with minimal manual labeling to address this challenge. The ventricular volume over time is assumed to be dominated by sparse frequencies corresponding to the heart and respiratory rates. Moreover, SBL identifies these sparse frequencies on well-segmented inner slices by optimizing hyperparameters via type -II likelihood, automatically pruning irrelevant components. The identified sparse frequencies guide the selection of outer slice images for labeling, minimizing posterior variance. This work provides performance guarantees for the greedy algorithm. Testing on patient data demonstrates that only a few labeled images are necessary for accurate volume prediction. The labeling procedure effectively avoids selecting inefficient images. Furthermore, the Bayesian approach provides uncertainty estimates, highlighting unreliable predictions (e.g., when choosing suboptimal labels).
Authors: Yuxiao Sun, Yao Zhao, Meiqin Liu, Chao Yao, Weisi Lin
Abstract: Currently, video transmission serves not only the Human Visual System (HVS) for viewing but also machine perception for analysis. However, existing codecs are primarily optimized for pixel-domain and HVS-perception metrics rather than the needs of machine vision tasks. To address this issue, we propose a Compression Distortion Representation Embedding (CDRE) framework, which extracts machine-perception-related distortion representation and embeds it into downstream models, addressing the information lost during compression and improving task performance. Specifically, to better analyze the machine-perception-related distortion, we design a compression-sensitive extractor that identifies compression degradation in the feature domain. For efficient transmission, a lightweight distortion codec is introduced to compress the distortion information into a compact representation. Subsequently, the representation is progressively embedded into the downstream model, enabling it to be better informed about compression degradation and enhancing performance. Experiments across various codecs and downstream tasks demonstrate that our framework can effectively boost the rate-task performance of existing codecs with minimal overhead in terms of bitrate, execution time, and number of parameters. Our codes and supplementary materials are released in https://github.com/Ws-Syx/CDRE/.
Authors: Brett Levac, Ajil Jalal, Kannan Ramchandran, Jonathan I. Tamir
Abstract: Blind inverse problems in imaging arise from uncertainties in the system used to collect (noisy) measurements of images. Recovering clean images from these measurements typically requires identifying the imaging system, either implicitly or explicitly. A common solution leverages generative models as priors for both the images and the imaging system parameters (e.g., a class of point spread functions). To learn these priors in a straightforward manner requires access to a dataset of clean images as well as samples of the imaging system. We propose an AmbientGAN-based generative technique to identify the distribution of parameters in unknown imaging systems, using only unpaired clean images and corrupted measurements. This learned distribution can then be used in model-based recovery algorithms to solve blind inverse problems such as blind deconvolution. We successfully demonstrate our technique for learning Gaussian blur and motion blur priors from noisy measurements and show their utility in solving blind deconvolution with diffusion posterior sampling.
Authors: Yuxue Hu, Junsong Li, Meixuan Chen, Dongyu Su, Tongguan Wang, Ying Sha
Abstract: Euphemism identification deciphers the true meaning of euphemisms, such as linking "weed" (euphemism) to "marijuana" (target keyword) in illicit texts, aiding content moderation and combating underground markets. While existing methods are primarily text-based, the rise of social media highlights the need for multimodal analysis, incorporating text, images, and audio. However, the lack of multimodal datasets for euphemisms limits further research. To address this, we regard euphemisms and their corresponding target keywords as keywords and first introduce a keyword-oriented multimodal corpus of euphemisms (KOM-Euph), involving three datasets (Drug, Weapon, and Sexuality), including text, images, and speech. We further propose a keyword-oriented multimodal euphemism identification method (KOM-EI), which uses cross-modal feature alignment and dynamic fusion modules to explicitly utilize the visual and audio features of the keywords for efficient euphemism identification. Extensive experiments demonstrate that KOM-EI outperforms state-of-the-art models and large language models, and show the importance of our multimodal datasets.
Authors: Yue Li, Meng Tian, Zhenyu Lin, Jiangtong Zhu, Dechang Zhu, Haiqiang Liu, Zining Wang, Yueyi Zhang, Zhiwei Xiong, Xinhai Zhao
Abstract: Existing benchmarks for Vision-Language Model (VLM) on autonomous driving (AD) primarily assess interpretability through open-form visual question answering (QA) within coarse-grained tasks, which remain insufficient to assess capabilities in complex driving scenarios. To this end, we introduce $\textbf{VLADBench}$, a challenging and fine-grained dataset featuring close-form QAs that progress from static foundational knowledge and elements to advanced reasoning for dynamic on-road situations. The elaborate $\textbf{VLADBench}$ spans 5 key domains: Traffic Knowledge Understanding, General Element Recognition, Traffic Graph Generation, Target Attribute Comprehension, and Ego Decision-Making and Planning. These domains are further broken down into 11 secondary aspects and 29 tertiary tasks for a granular evaluation. A thorough assessment of general and domain-specific (DS) VLMs on this benchmark reveals both their strengths and critical limitations in AD contexts. To further exploit the cognitive and reasoning interactions among the 5 domains for AD understanding, we start from a small-scale VLM and train the DS models on individual domain datasets (collected from 1.4M DS QAs across public sources). The experimental results demonstrate that the proposed benchmark provides a crucial step toward a more comprehensive assessment of VLMs in AD, paving the way for the development of more cognitively sophisticated and reasoning-capable AD systems.
Authors: Samuel Bilson, Anna Pustogvar
Abstract: Land cover classification involves the production of land cover maps, which determine the type of land through remote sensing imagery. Over recent years, such classification is being performed by machine learning classification models, which can give highly accurate predictions on land cover per pixel using large quantities of input training data. However, such models do not currently take account of input measurement uncertainty, which is vital for traceability in metrology. In this work we propose a Bayesian classification framework using generative modelling to take account of input measurement uncertainty. We take the specific case of Bayesian quadratic discriminant analysis, and apply it to land cover datasets from Copernicus Sentinel-2 in 2020 and 2021. We benchmark the performance of the model against more popular classification models used in land cover maps such as random forests and neural networks. We find that such Bayesian models are more trustworthy, in the sense that they are more interpretable, explicitly model the input measurement uncertainty, and maintain predictive performance of class probability outputs across datasets of different years and sizes, whilst also being computationally efficient.
Authors: Hyunjun Lee, Hyunsoo Lee, Sookwan Han
Abstract: There have been many attempts to leverage multiple diffusion models for collaborative generation, extending beyond the original domain. A prominent approach involves synchronizing multiple diffusion trajectories by mixing the estimated scores to artificially correlate the generation processes. However, existing methods rely on naive heuristics, such as averaging, without considering task specificity. These approaches do not clarify why such methods work and often fail when a heuristic suitable for one task is blindly applied to others. In this paper, we present a probabilistic framework for analyzing why diffusion synchronization works and reveal where heuristics should be focused - modeling correlations between multiple trajectories and adapting them to each specific task. We further identify optimal correlation models per task, achieving better results than previous approaches that apply a single heuristic across all tasks without justification.
Authors: Yassir Lairgi
Abstract: The accurate determination of the beginning of each Hijri month is essential for religious, cultural, and administrative purposes. Manazel (The code and datasets are available at https://github.com/lairgiyassir/manazel) addresses this challenge in Morocco by leveraging 13 years of crescent visibility data to refine the ODEH criterion, a widely used standard for lunar crescent visibility prediction. The study integrates two key features, the Arc of Vision (ARCV) and the total width of the crescent (W), to enhance the accuracy of lunar visibility assessments. A machine learning approach utilizing the Logistic Regression algorithm is employed to classify crescent visibility conditions, achieving a predictive accuracy of 98.83%. This data-driven methodology offers a robust and reliable framework for determining the start of the Hijri month, comparing different data classification tools, and improving the consistency of lunar calendar calculations in Morocco. The findings demonstrate the effectiveness of machine learning in astronomical applications and highlight the potential for further enhancements in the modeling of crescent visibility.
Authors: Danaja Rutar, Alva Markelius, Konstantinos Voudouris, Jos\'e Hern\'andez-Orallo, Lucy Cheke
Abstract: One of the core components of our world models is 'intuitive physics' - an understanding of objects, space, and causality. This capability enables us to predict events, plan action and navigate environments, all of which rely on a composite sense of objecthood. Despite its importance, there is no single, unified account of objecthood, though multiple theoretical frameworks provide insights. In the first part of this paper, we present a comprehensive overview of the main theoretical frameworks in objecthood research - Gestalt psychology, enactive cognition, and developmental psychology - and identify the core capabilities each framework attributes to object understanding, as well as what functional roles they play in shaping world models in biological agents. Given the foundational role of objecthood in world modelling, understanding objecthood is also essential in AI. In the second part of the paper, we evaluate how current AI paradigms approach and test objecthood capabilities compared to those in cognitive science. We define an AI paradigm as a combination of how objecthood is conceptualised, the methods used for studying objecthood, the data utilised, and the evaluation techniques. We find that, whilst benchmarks can detect that AI systems model isolated aspects of objecthood, the benchmarks cannot detect when AI systems lack functional integration across these capabilities, not solving the objecthood challenge fully. Finally, we explore novel evaluation approaches that align with the integrated vision of objecthood outlined in this paper. These methods are promising candidates for advancing from isolated object capabilities toward general-purpose AI with genuine object understanding in real-world contexts.
Authors: Zhiyuan Ma, Xinyue Liang, Rongyuan Wu, Xiangyu Zhu, Zhen Lei, Lei Zhang
Abstract: It is highly desirable to obtain a model that can generate high-quality 3D meshes from text prompts in just seconds. While recent attempts have adapted pre-trained text-to-image diffusion models, such as Stable Diffusion (SD), into generators of 3D representations (e.g., Triplane), they often suffer from poor quality due to the lack of sufficient high-quality 3D training data. Aiming at overcoming the data shortage, we propose a novel training scheme, termed as Progressive Rendering Distillation (PRD), eliminating the need for 3D ground-truths by distilling multi-view diffusion models and adapting SD into a native 3D generator. In each iteration of training, PRD uses the U-Net to progressively denoise the latent from random noise for a few steps, and in each step it decodes the denoised latent into 3D output. Multi-view diffusion models, including MVDream and RichDreamer, are used in joint with SD to distill text-consistent textures and geometries into the 3D outputs through score distillation. Since PRD supports training without 3D ground-truths, we can easily scale up the training data and improve generation quality for challenging text prompts with creative concepts. Meanwhile, PRD can accelerate the inference speed of the generation model in just a few steps. With PRD, we train a Triplane generator, namely TriplaneTurbo, which adds only $2.5\%$ trainable parameters to adapt SD for Triplane generation. TriplaneTurbo outperforms previous text-to-3D generators in both efficiency and quality. Specifically, it can produce high-quality 3D meshes in 1.2 seconds and generalize well for challenging text input. The code is available at https://github.com/theEricMa/TriplaneTurbo.
Authors: Wenqi Zhang, Mengna Wang, Gangao Liu, Xu Huixin, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Weiming Lu, Peng Li, Yueting Zhuang
Abstract: Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with environments through image action interleaved trajectories remains largely -unexplored. We present Embodied Reasoner, a model that extends o1 style reasoning to interactive embodied search tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k interactive images and 90k diverse thinking processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training pipeline that progressively enhances the model's capabilities through imitation learning, self-exploration via rejection sampling, and self-correction through reflection tuning. The evaluation shows that our model significantly outperforms those advanced visual reasoning models, e.g., it exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9\%, 24\%, and +13\%. Analysis reveals our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world environments also show our superiority while exhibiting fewer repeated searches and logical inconsistency cases.
Authors: Liuyue Xie, George Z. Wei, Avik Kuthiala, Ce Zheng, Ananya Bal, Mosam Dabhi, Liting Wen, Taru Rustagi, Ethan Lai, Sushil Khyalia, Rohan Choudhury, Morteza Ziyadi, Xu Zhang, Hao Yang, L\'aszl\'o A. Jeni
Abstract: Frontier models have either been language-only or have primarily focused on vision and language modalities. Although recent advancements in models with vision and audio understanding capabilities have shown substantial progress, the field lacks a standardized evaluation framework for thoroughly assessing their cross-modality perception performance. We introduce MAVERIX~(Multimodal Audio-Visual Evaluation Reasoning IndeX), a novel benchmark with 700 videos and 2,556 questions explicitly designed to evaluate multimodal models through tasks that necessitate close integration of video and audio information. MAVERIX uniquely provides models with audiovisual tasks, closely mimicking the multimodal perceptual experiences available to humans during inference and decision-making processes. To our knowledge, MAVERIX is the first benchmark aimed explicitly at assessing comprehensive audiovisual integration. Experiments with state-of-the-art models, including Gemini 1.5 Pro and o1, show performance approaching human levels (around 70% accuracy), while human experts reach near-ceiling performance (95.1%). With standardized evaluation protocols, a rigorously annotated pipeline, and a public toolkit, MAVERIX establishes a challenging testbed for advancing audiovisual multimodal intelligence.
Authors: Kun Yuan, Vinkle Srivastav, Tong Yu, Joel L. Lavanchy, Jacques Marescaux, Pietro Mascagni, Nassir Navab, Nicolas Padoy
Abstract: Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning without relying on manual annotations. We address the surgery-specific linguistic challenges present in surgical video lectures by employing multiple complementary automatic speech recognition systems to generate text transcriptions. We then present a novel method, SurgVLP - Surgical Vision Language Pre-training, for multi-modal representation learning. Extensive experiments across diverse surgical procedures and tasks demonstrate that the multi-modal representations learned by SurgVLP exhibit strong transferability and adaptability in surgical video analysis. Furthermore, our zero-shot evaluations highlight SurgVLP's potential as a general-purpose foundation model for surgical workflow analysis, reducing the reliance on extensive manual annotations for downstream tasks, and facilitating adaptation methods such as few-shot learning to build a scalable and data-efficient solution for various downstream surgical applications. The [training code](https://github.com/CAMMA-public/SurgVLP) and [weights](https://github.com/CAMMA-public/PeskaVLP) are public.
URLs: https://github.com/CAMMA-public/SurgVLP), https://github.com/CAMMA-public/PeskaVLP)
Authors: Haolin Xiong, Sairisheek Muttukuru, Rishi Upadhyay, Pradyumna Chari, Achuta Kadambi
Abstract: 3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis. However, this technique requires dense training views to accurately reconstruct 3D geometry. A limited number of input views will significantly degrade reconstruction quality, resulting in artifacts such as "floaters" and "background collapse" at unseen viewpoints. In this work, we introduce SparseGS, an efficient training pipeline designed to address the limitations of 3DGS in scenarios with sparse training views. SparseGS incorporates depth priors, novel depth rendering techniques, and a pruning heuristic to mitigate floater artifacts, alongside an Unseen Viewpoint Regularization module to alleviate background collapses. Our extensive evaluations on the Mip-NeRF360, LLFF, and DTU datasets demonstrate that SparseGS achieves high-quality reconstruction in both unbounded and forward-facing scenarios, with as few as 12 and 3 input images, respectively, while maintaining fast training and real-time rendering capabilities.
Authors: Yibo Xia, Lizhen Wang, Xiang Deng, Xiaoyan Luo, Yunhong Wang, Yebin Liu
Abstract: Synthesizing high-fidelity and emotion-controllable talking video portraits, with audio-lip sync, vivid expressions, realistic head poses, and eye blinks, has been an important and challenging task in recent years. Most existing methods suffer in achieving personalized and precise emotion control, smooth transitions between different emotion states, and the generation of diverse motions. To tackle these challenges, we present GMTalker, a Gaussian mixture-based emotional talking portraits generation framework. Specifically, we propose a Gaussian mixture-based expression generator that can construct a continuous and disentangled latent space, achieving more flexible emotion manipulation. Furthermore, we introduce a normalizing flow-based motion generator pretrained on a large dataset with a wide-range motion to generate diverse head poses, blinks, and eyeball movements. Finally, we propose a personalized emotion-guided head generator with an emotion mapping network that can synthesize high-fidelity and faithful emotional video portraits. Both quantitative and qualitative experiments demonstrate our method outperforms previous methods in image quality, photo-realism, emotion accuracy, and motion diversity.
Authors: Dong Zhang, Pingcheng Dong, Long Chen, Kwang-Ting Cheng
Abstract: It has been revealed that small efficient dense image prediction (EDIP) models, trained using the knowledge distillation (KD) framework, encounter two key challenges, including maintaining boundary region completeness and preserving target region connectivity, despite their favorable capacity to recognize main object regions. In this work, we propose a complementary boundary and context distillation (BCD) method within the KD framework for EDIPs, which facilitates the targeted knowledge transfer from large accurate teacher models to compact efficient student models. Specifically, the boundary distillation component focuses on extracting explicit object-level semantic boundaries from the hierarchical feature maps of the backbone network to enhance the student model's mask quality in boundary regions. Concurrently, the context distillation component leverages self-relations as a bridge to transfer implicit pixel-level contexts from the teacher model to the student model, ensuring strong connectivity in target regions. Our proposed BCD method is specifically designed for EDIP tasks and is characterized by its simplicity and efficiency. Extensive experimental results across semantic segmentation, object detection, and instance segmentation on various representative datasets demonstrate that our method can outperform existing methods without requiring extra supervisions or incurring increased inference costs, resulting in well-defined object boundaries and smooth connecting regions.
Authors: Fabio Tosi, Youmin Zhang, Ziren Gong, Erik Sandstr\"om, Stefano Mattoccia, Martin R. Oswald, Matteo Poggi
Abstract: Over the past two decades, research in the field of Simultaneous Localization and Mapping (SLAM) has undergone a significant evolution, highlighting its critical role in enabling autonomous exploration of unknown environments. This evolution ranges from hand-crafted methods, through the era of deep learning, to more recent developments focused on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) representations. Recognizing the growing body of research and the absence of a comprehensive survey on the topic, this paper aims to provide the first comprehensive overview of SLAM progress through the lens of the latest advancements in radiance fields. It sheds light on the background, evolutionary path, inherent strengths and limitations, and serves as a fundamental reference to highlight the dynamic progress and specific challenges.
Authors: Hanlin Wang, Zhan Tong, Kecheng Zheng, Yujun Shen, Limin Wang
Abstract: The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name and provide reasonable, contextual descriptions to help audience understand the storyline of movie. To achieve this goal, we propose to leverage pre-trained foundation models through a simple and unified framework to generate ADs with interleaved multimodal sequence as input, termed as Uni-AD. To enhance the alignment of features across various modalities with finer granularity, we introduce a simple and lightweight module that maps video features into the textual feature space. Moreover, we also propose a character-refinement module to provide more precise information by identifying the main characters who play more significant roles in the video context. With these unique designs, we further incorporate contextual information and a contrastive loss into our architecture to generate smoother and more contextually appropriate ADs. Experiments on multiple AD datasets show that Uni-AD performs well on AD generation, which demonstrates the effectiveness of our approach. Our code is available at: https://github.com/ant-research/UniAD.
Authors: Juhong Min, Shyamal Buch, Arsha Nagrani, Minsu Cho, Cordelia Schmid
Abstract: This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular reasoning framework. Previous modular methods have shown promise with a single planning stage ungrounded in visual content. However, through a simple and effective baseline, we find that such systems can lead to brittle behavior in practice for challenging videoQA settings. Thus, unlike traditional single-stage planning methods, we propose a multi-stage system consisting of an event parser, a grounding stage, and a final reasoning stage in conjunction with an external memory. All stages are training-free, and performed using few-shot prompting of large models, creating interpretable intermediate outputs at each stage. By decomposing the underlying planning and task complexity, our method, MoReVQA, improves over prior work on standard videoQA benchmarks (NExT-QA, iVQA, EgoSchema, ActivityNet-QA) with state-of-the-art results, and extensions to related tasks (grounded videoQA, paragraph captioning).
Authors: Weijie Lyu, Xueting Li, Abhijit Kundu, Yi-Hsuan Tsai, Ming-Hsuan Yang
Abstract: We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Contrasted to prior 3D scene segmentation approaches that rely on video object tracking or contrastive learning methods, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses through a novel 3D-aware memory bank. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial for sparsely sampled images, ensuring precise mask label consistency. Furthermore, Gaga accommodates 2D segmentation masks from diverse sources and demonstrates robust performance with different open-world zero-shot class-agnostic segmentation models, significantly enhancing its versatility. Extensive qualitative and quantitative evaluations demonstrate that Gaga performs favorably against state-of-the-art methods, emphasizing its potential for real-world applications such as 3D scene understanding and manipulation.
Authors: Matthias Streller, So\v{n}a Michl\'ikov\'a, Willy Ciecior, Katharina L\"onnecke, Leoni A. Kunz-Schughart, Steffen Lange, Anja Voss-B\"ohme
Abstract: Multicellular tumor spheroids (MCTS) are advanced cell culture systems for assessing the impact of combinatorial radio(chemo)therapy. They exhibit therapeutically relevant in-vivo-like characteristics from 3D cell-cell and cell-matrix interactions to radial pathophysiological gradients related to proliferative activity and nutrient/oxygen supply, altering cellular radioresponse. State-of-the-art assays quantify long-term curative endpoints based on collected brightfield image time series from large treated spheroid populations per irradiation dose and treatment arm. Here, spheroid control probabilities are documented analogous to in-vivo tumor control probabilities based on Kaplan-Meier curves. This analyses require laborious spheroid segmentation of up to 100.000 images per treatment arm to extract relevant structural information from the images, e.g., diameter, area, volume and circularity. While several image analysis algorithms are available for spheroid segmentation, they all focus on compact MCTS with clearly distinguishable outer rim throughout growth. However, treated MCTS may partly be detached and destroyed and are usually obscured by dead cell debris. We successfully train two Fully Convolutional Networks, UNet and HRNet, and optimize their hyperparameters to develop an automatic segmentation for both untreated and treated MCTS. We systematically validate the automatic segmentation on larger, independent data sets of spheroids derived from two human head-and-neck cancer cell lines. We find an excellent overlap between manual and automatic segmentation for most images, quantified by Jaccard indices at around 90%. For images with smaller overlap of the segmentations, we demonstrate that this error is comparable to the variations across segmentations from different biological experts, suggesting that these images represent biologically unclear or ambiguous cases.
Authors: Abdelrahman Abdelhamed, Mahmoud Afifi, Alec Go
Abstract: Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs. Using multimodal LLMs, we generate comprehensive textual representations from input images. These textual representations are then utilized to generate fixed-dimensional features in a cross-modal embedding space. Subsequently, these features are fused together to perform zero-shot classification using a linear classifier. Our method does not require prompt engineering for each dataset; instead, we use a single, straightforward set of prompts across all datasets. We evaluated our method on several datasets and our results demonstrate its remarkable effectiveness, surpassing benchmark accuracy on multiple datasets. On average, for ten benchmarks, our method achieved an accuracy gain of 6.2 percentage points, with an increase of 6.8 percentage points on the ImageNet dataset, compared to prior methods re-evaluated with the same setup. Our findings highlight the potential of multimodal LLMs to enhance computer vision tasks such as zero-shot image classification, offering a significant improvement over traditional methods.
Authors: Jing Gu, Yuwei Fang, Ivan Skorokhodov, Peter Wonka, Xinya Du, Sergey Tulyakov, Xin Eric Wang
Abstract: Video editing serves as a fundamental pillar of digital media, spanning applications in entertainment, education, and professional communication. However, previous methods often overlook the necessity of comprehensively understanding both global and local contexts, leading to inaccurate and inconsistent edits in the spatiotemporal dimension, especially for long videos. In this paper, we introduce VIA, a unified spatiotemporal Video Adaptation framework for global and local video editing, pushing the limits of consistently editing minute-long videos. First, to ensure local consistency within individual frames, we designed test-time editing adaptation to adapt a pre-trained image editing model for improving consistency between potential editing directions and the text instruction, and adapts masked latent variables for precise local control. Furthermore, to maintain global consistency over the video sequence, we introduce spatiotemporal adaptation that recursively gather consistent attention variables in key frames and strategically applies them across the whole sequence to realize the editing effects. Extensive experiments demonstrate that, compared to baseline methods, our VIA approach produces edits that are more faithful to the source videos, more coherent in the spatiotemporal context, and more precise in local control. More importantly, we show that VIA can achieve consistent long video editing in minutes, unlocking the potential for advanced video editing tasks over long video sequences.
Authors: Xiang Gao, Zhengbo Xu, Junhan Zhao, Jiaying Liu
Abstract: Recently, large-scale text-to-image (T2I) diffusion models have emerged as a powerful tool for image-to-image translation (I2I), allowing open-domain image translation via user-provided text prompts. This paper proposes frequency-controlled diffusion model (FCDiffusion), an end-to-end diffusion-based framework that contributes a novel solution to text-guided I2I from a frequency-domain perspective. At the heart of our framework is a feature-space frequency-domain filtering module based on Discrete Cosine Transform, which filters the latent features of the source image in the DCT domain, yielding filtered image features bearing different DCT spectral bands as different control signals to the pre-trained Latent Diffusion Model. We reveal that control signals of different DCT spectral bands bridge the source image and the T2I generated image in different correlations (e.g., style, structure, layout, contour, etc.), and thus enable versatile I2I applications emphasizing different I2I correlations, including style-guided content creation, image semantic manipulation, image scene translation, and image style translation. Different from related approaches, FCDiffusion establishes a unified text-guided I2I framework suitable for diverse image translation tasks simply by switching among different frequency control branches at inference time. The effectiveness and superiority of our method for text-guided I2I are demonstrated with extensive experiments both qualitatively and quantitatively. Our project is publicly available at: https://xianggao1102.github.io/FCDiffusion/.
Authors: Zhantao Yang, Ruili Feng, Keyu Yan, Huangji Wang, Zhicai Wang, Shangwen Zhu, Han Zhang, Jie Xiao, Pingyu Wu, Kai Zhu, Jixuan Chen, Chen-Wei Xie, Yue Yang, Hongyang Zhang, Yu Liu, Fan Cheng
Abstract: Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions often carry lengthy, intertwined contexts that are difficult to parse and frequently overlook essential cues, posing a great barrier for models like GroundingDINO and SDXL, which lack the strong text encoding and syntax analysis needed to fully leverage dense captions. To address this, we propose BACON, a prompting method that breaks down VLM-generated captions into disentangled, structured elements such as objects, relationships, styles, and themes. This approach not only minimizes confusion from handling complex contexts but also allows for efficient transfer into a JSON dictionary, enabling models without linguistic processing capabilities to easily access key information. We annotated 100,000 image-caption pairs using BACON with GPT-4V and trained an LLaVA captioner on this dataset, enabling it to produce BACON-style captions without relying on costly GPT-4V. Evaluations of overall quality, precision, and recall-as well as user studies-demonstrate that the resulting caption model consistently outperforms other SOTA VLM models in generating high-quality captions. Besides, we show that BACON-style captions exhibit better clarity when applied to various models, enabling them to accomplish previously unattainable tasks or surpass existing SOTA solutions without training. For example, BACON-style captions help GroundingDINO achieve 1.51x higher recall scores on open-vocabulary object detection tasks compared to leading methods.
Authors: Liuyue Xie, Joel Julin, Koichiro Niinuma, Laszlo A. Jeni
Abstract: Gaussian Splatting and its dynamic extensions are effective for reconstructing 3D scenes from 2D images when there is significant camera movement to facilitate motion parallax and when scene objects remain relatively static. However, in many real-world scenarios, these conditions are not met. As a consequence, data-driven semantic and geometric priors have been favored as regularizers, despite their bias toward training data and their neglect of broader movement dynamics. Departing from this practice, we propose a novel analytical approach that adapts the classical Lucas-Kanade method to dynamic Gaussian splatting. By leveraging the intrinsic properties of the forward warp field network, we derive an analytical velocity field that, through time integration, facilitates accurate scene flow computation. This enables the precise enforcement of motion constraints on warp fields, thus constraining both 2D motion and 3D positions of the Gaussians. Our method excels in reconstructing highly dynamic scenes with minimal camera movement, as demonstrated through experiments on both synthetic and real-world scenes.
Authors: Asma Khan, Tushar Kataria, Janmesh Ukey, Shireen Y. Elhabian
Abstract: Statistical Shape Models (SSMs) excel at identifying population level anatomical variations, which is at the core of various clinical and biomedical applications, including morphology-based diagnostics and surgical planning. However, the effectiveness of SSM is often constrained by the necessity for expert-driven manual segmentation, a process that is both time-intensive and expensive, thereby restricting their broader application and utility. Recent deep learning approaches enable the direct estimation of Statistical Shape Models (SSMs) from unsegmented images. While these models can predict SSMs without segmentation during deployment, they do not address the challenge of acquiring the manual annotations needed for training, particularly in resource-limited settings. Semi-supervised models for anatomy segmentation can mitigate the annotation burden. Yet, despite the abundance of available approaches, there are no established guidelines to inform end-users on their effectiveness for the downstream task of constructing SSMs. In this study, we systematically evaluate the potential of semi-supervised methods as viable alternatives to manual segmentations for building SSMs. We establish a new performance benchmark by employing various semi-supervised methods for anatomy segmentation under low annotation settings, utilizing the predicted segmentations for the task of SSM. Our results indicate that some methods produce noisy segmentation, which is very unfavorable for SSM tasks, while others can capture the correct modes of variations in the population cohort with 60-80% reduction in required manual annotation
Authors: Yesheng Zhang, Shuhan Shen, Xu Zhao
Abstract: We propose MESA and DMESA as novel feature matching methods, which utilize Segment Anything Model (SAM) to effectively mitigate matching redundancy. The key insight of our methods is to establish implicit-semantic area matching prior to point matching, based on advanced image understanding of SAM. Then, informative area matches with consistent internal semantic are able to undergo dense feature comparison, facilitating precise inside-area point matching. Specifically, MESA adopts a sparse matching framework and first obtains candidate areas from SAM results through a novel Area Graph (AG). Then, area matching among the candidates is formulated as graph energy minimization and solved by graphical models derived from AG. To address the efficiency issue of MESA, we further propose DMESA as its dense counterpart, applying a dense matching framework. After candidate areas are identified by AG, DMESA establishes area matches through generating dense matching distributions. The distributions are produced from off-the-shelf patch matching utilizing the Gaussian Mixture Model and refined via the Expectation Maximization. With less repetitive computation, DMESA showcases a speed improvement of nearly five times compared to MESA, while maintaining competitive accuracy. Our methods are extensively evaluated on five datasets encompassing indoor and outdoor scenes. The results illustrate consistent performance improvements from our methods for five distinct point matching baselines across all datasets. Furthermore, our methods exhibit promise generalization and improved robustness against image resolution variations. The code is publicly available at https://github.com/Easonyesheng/A2PM-MESA.
Authors: Fuchen Zheng, Xuhang Chen, Weihuang Liu, Haolun Li, Yingtie Lei, Jiahui He, Chi-Man Pun, Shounjun Zhou
Abstract: In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture that fuses multiple attention mechanisms for enhanced segmentation of small tumors and organs. SMAFormer can capture both local and global features for medical image segmentation. The architecture comprises two pivotal components. First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment. Second, addressing the challenge of information loss incurred during attention mechanism transitions and feature fusion, we design a Feature Fusion Modulator. This module bolsters the integration between the channel and spatial attention by mitigating reshaping-induced information attrition. To evaluate our method, we conduct extensive experiments on various medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, achieving state-of-the-art results. Code and models are available at: https://github.com/CXH-Research/SMAFormer.
Authors: Stefano Esposito, Anpei Chen, Christian Reiser, Samuel Rota Bul\`o, Lorenzo Porzi, Katja Schwarz, Christian Richardt, Michael Zollh\"ofer, Peter Kontschieder, Andreas Geiger
Abstract: High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy geometry like hair. In turn, alpha-blending techniques excel at representing fuzzy materials but require an unbounded number of samples per ray (P1). Further overheads are induced by empty space skipping in volume rendering (P2) and sorting input primitives in splatting (P3). We present a novel representation for real-time view synthesis where the (P1) number of sampling locations is small and bounded, (P2) sampling locations are efficiently found via rasterization, and (P3) rendering is sorting-free. We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order. First, we model surface layers as signed distance function (SDF) shells with optimal spacing learned during training. Then, we bake them as meshes and fit UV textures. Unlike single-surface methods, our multi-layer representation effectively models fuzzy objects. In contrast to volume and splatting-based methods, our approach enables real-time rendering on low-power laptops and smartphones.
Authors: Jingfan Yang, Hu Gao, Ying Zhang, Bowen Ma, Depeng Dang
Abstract: Spacecraft image denoising is a crucial fundamental technology closely related to aerospace research. However, the existing deep learning-based image denoising methods are primarily designed for natural image and fail to adequately consider the characteristics of spacecraft image(e.g. low-light conditions, repetitive periodic structures), resulting in suboptimal performance in the spacecraft image denoising task. To address the aforementioned problems, we propose a Structure modeling Activation Free Fourier Network (SAFFN), which is an efficient spacecraft image denoising method including Structure Modeling Block (SMB) and Activation Free Fourier Block (AFFB). We present SMB to effectively extract edge information and model the structure for better identification of spacecraft components from dark regions in spacecraft noise image. We present AFFB and utilize an improved Fast Fourier block to extract repetitive periodic features and long-range information in noisy spacecraft image. Extensive experimental results demonstrate that our SAFFN performs competitively compared to the state-of-the-art methods on spacecraft noise image datasets. The codes are available at: https://github.com/shenduke/SAFFN.
Authors: Amirreza Mahbod, Nematollah Saeidi, Sepideh Hatamikia, Ramona Woitek
Abstract: Medical image retrieval refers to the task of finding similar images for given query images in a database, with applications such as diagnosis support. While traditional medical image retrieval relied on clinical metadata, content-based medical image retrieval (CBMIR) depends on image features, which can be extracted automatically or semi-automatically. Many approaches have been proposed for CBMIR, and among them, using pre-trained convolutional neural networks (CNNs) is a widely utilized approach. However, considering the recent advances in the development of foundation models for various computer vision tasks, their application for CBMIR can also be investigated. In this study, we used several pre-trained feature extractors from well-known pre-trained CNNs and pre-trained foundation models and investigated the CBMIR performance on eight types of two-dimensional (2D) and three-dimensional (3D) medical images. Furthermore, we investigated the effect of image size on the CBMIR performance. Our results show that, overall, for the 2D datasets, foundation models deliver superior performance by a large margin compared to CNNs, with the general-purpose self-supervised model for computational pathology (UNI) providing the best overall performance across all datasets and image sizes. For 3D datasets, CNNs and foundation models deliver more competitive performance, with contrastive learning from captions for histopathology model (CONCH) achieving the best overall performance. Moreover, our findings confirm that while using larger image sizes (especially for 2D datasets) yields slightly better performance, competitive CBMIR performance can still be achieved even with smaller image sizes. Our codes to reproduce the results are available at: https://github.com/masih4/MedImageRetrieval.
Authors: Hamid Suleman, Syed Talal Wasim, Muzammal Naseer, Juergen Gall
Abstract: State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent matrices. The Mamba model addressed this with data-dependent variants via the S6 selective-scan algorithm, enhancing context modeling, especially for long sequences. However, Mamba-based architectures are difficult to scale with respect to the number of parameters, which is a major limitation for vision applications. This paper addresses the scalability issue of large SSMs for image classification and action recognition without requiring additional techniques like knowledge distillation. We analyze the distinct characteristics of Mamba-based and Attention-based models, proposing a Mamba-Attention interleaved architecture that enhances scalability, robustness, and performance. We demonstrate that the stable and efficient interleaved architecture resolves the scalability issue of Mamba-based architectures for images and videos and increases robustness to common artifacts like JPEG compression. Our thorough evaluation on the ImageNet-1K, Kinetics-400 and Something-Something-v2 benchmarks demonstrates that our approach improves the accuracy of state-of-the-art Mamba-based architectures by up to $+1.7$.
Authors: Yuzhe Wu, Yipeng Xu, Tianyu Xu, Jialu Zhang, Jianfeng Ren, Xudong Jiang
Abstract: Exemplar-Free Counting aims to count objects of interest without intensive annotations of objects or exemplars. To achieve this, we propose a Gated Context-Aware Swin-UNet (GCA-SUNet) to directly map an input image to the density map of countable objects. Specifically, a set of Swin transformers form an encoder to derive a robust feature representation, and a Gated Context-Aware Modulation block is designed to suppress irrelevant objects or background through a gate mechanism and exploit the attentive support of objects of interest through a self-similarity matrix. The gate strategy is also incorporated into the bottleneck network and the decoder of the Swin-UNet to highlight the features most relevant to objects of interest. By explicitly exploiting the attentive support among countable objects and eliminating irrelevant features through the gate mechanisms, the proposed GCA-SUNet focuses on and counts objects of interest without relying on predefined categories or exemplars. Experimental results on the real-world datasets such as FSC-147 and CARPK demonstrate that GCA-SUNet significantly and consistently outperforms state-of-the-art methods. The code is available at https://github.com/Amordia/GCA-SUNet.
Authors: Rolandos Alexandros Potamias, Jinglei Zhang, Jiankang Deng, Stefanos Zafeiriou
Abstract: In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics. In contrast, there has been a notable gap in hand detection pipelines, posing significant challenges in constructing effective real-world multi-hand reconstruction systems. In this work, we present a data-driven pipeline for efficient multi-hand reconstruction in the wild. The proposed pipeline is composed of two components: a real-time fully convolutional hand localization and a high-fidelity transformer-based 3D hand reconstruction model. To tackle the limitations of previous methods and build a robust and stable detection network, we introduce a large-scale dataset with over than 2M in-the-wild hand images with diverse lighting, illumination, and occlusion conditions. Our approach outperforms previous methods in both efficiency and accuracy on popular 2D and 3D benchmarks. Finally, we showcase the effectiveness of our pipeline to achieve smooth 3D hand tracking from monocular videos, without utilizing any temporal components. Code, models, and dataset are available https://rolpotamias.github.io/WiLoR.
Authors: Ilya Chugunov, Amogh Joshi, Kiran Murthy, Francois Bleibel, Felix Heide
Abstract: Challenging to capture, and challenging to display on a cellphone screen, the panorama paradoxically remains both a staple and underused feature of modern mobile camera applications. In this work we address both of these challenges with a spherical neural light field model for implicit panoramic image stitching and re-rendering; able to accommodate for depth parallax, view-dependent lighting, and local scene motion and color changes during capture. Fit during test-time to an arbitrary path panoramic video capture -- vertical, horizontal, random-walk -- these neural light spheres jointly estimate the camera path and a high-resolution scene reconstruction to produce novel wide field-of-view projections of the environment. Our single-layer model avoids expensive volumetric sampling, and decomposes the scene into compact view-dependent ray offset and color components, with a total model size of 80 MB per scene, and real-time (50 FPS) rendering at 1080p resolution. We demonstrate improved reconstruction quality over traditional image stitching and radiance field methods, with significantly higher tolerance to scene motion and non-ideal capture settings.
Authors: Yuexi Du, John Onofrey, Nicha C. Dvornek
Abstract: Contrastive Language-Image Pre-training (CLIP) demonstrates strong potential in medical image analysis but requires substantial data and computational resources. Due to these restrictions, existing CLIP applications in medical imaging focus mainly on modalities like chest X-rays that have abundant image-report data available, leaving many other important modalities underexplored. Here, we propose one of the first adaptations of the full CLIP model to mammography, which presents significant challenges due to labeled data scarcity, high-resolution images with small regions of interest, and class-wise imbalance. We first develop a specialized supervision framework for mammography that leverages its multi-view nature. Furthermore, we design a symmetric local alignment module to better focus on detailed features in high-resolution images. Lastly, we incorporate a parameter-efficient fine-tuning approach for large language models pre-trained with medical knowledge to address data limitations. Our multi-view and multi-scale alignment (MaMA) method outperforms state-of-the-art baselines for three different tasks on two large real-world mammography datasets, EMBED and RSNA-Mammo, with only 52% model size compared with the largest baseline. The code is available at https://github.com/XYPB/MaMA
Authors: Hongze Chen, Zehong Lin, Jun Zhang
Abstract: We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading processes of objects is essential for achieving high-fidelity results. Therefore, it is critical to incorporate global illumination to account for indirect lighting that reaches an object after multiple bounces across the scene. Previous 3DGS-based methods have attempted to model indirect lighting by characterizing indirect illumination as learnable lighting volumes or additional attributes of each Gaussian, while using baked occlusion to represent shadow effects. These methods, however, fail to accurately model the complex physical interactions between light and objects, making it impossible to construct realistic indirect illumination during relighting. To address this limitation, we propose to calculate indirect lighting using efficient path tracing with deferred shading. In our framework, we first render a G-buffer to capture the detailed geometry and material properties of the scene. Then, we perform physically-based rendering (PBR) only for direct lighting. With the G-buffer and previous rendering results, the indirect lighting can be calculated through a lightweight path tracing. Our method effectively models indirect lighting under any given lighting conditions, thereby achieving better novel view synthesis and competitive relighting. Quantitative and qualitative results show that our GI-GS outperforms existing baselines in both rendering quality and efficiency.
Authors: Jingqi Zhou, Sheng Wang, Jingwei Dong, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu
Abstract: Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation. To tackle this issue, we first identify the drawbacks of existing solutions (i.e., insufficient and irrelevant visual descriptions, and limited multi-modal capacities). We then decompose visual reasoning process into two stages: visual perception (i.e., eyesight) and textual reasoning (i.e., wisdom), and introduce a novel visual reasoning framework named ProReason. This framework features multi-run proactive perception and decoupled vision-reasoning capabilities. Briefly, given a multi-modal question, ProReason iterates proactive information collection and reasoning until the answer can be concluded with necessary and sufficient visual descriptions. Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs. Our extensive experiments demonstrate that ProReason outperforms both existing multi-step reasoning frameworks and passive peer methods on a wide range of benchmarks for both open-source and closed-source models. In addition, with the assistance of LLMs, ProReason achieves a performance improvement of up to 15% on MMMU benchmark. Our insights into existing solutions and the decoupled perspective for feasible integration of LLMs illuminate future research on visual reasoning techniques, especially LLM-assisted ones.
Authors: Ziming Huang, Xurui Li, Haotian Liu, Feng Xue, Yuzhe Wang, Yu Zhou
Abstract: Recently, multi-class anomaly classification has garnered increasing attention. Previous methods directly cluster anomalies but often struggle due to the lack of anomaly-prior knowledge. Acquiring this knowledge faces two issues: the non-prominent and weak-semantics anomalies. In this paper, we propose AnomalyNCD, a multi-class anomaly classification network compatible with different anomaly detection methods. To address the non-prominence of anomalies, we design main element binarization (MEBin) to obtain anomaly-centered images, ensuring anomalies are learned while avoiding the impact of incorrect detections. Next, to learn anomalies with weak semantics, we design mask-guided representation learning, which focuses on isolated anomalies guided by masks and reduces confusion from erroneous inputs through corrected pseudo labels. Finally, to enable flexible classification at both region and image levels, we develop a region merging strategy that determines the overall image category based on the classified anomaly regions. Our method outperforms the state-of-the-art works on the MVTec AD and MTD datasets. Compared with the current methods, AnomalyNCD combined with zero-shot anomaly detection method achieves a 10.8% $F_1$ gain, 8.8% NMI gain, and 9.5% ARI gain on MVTec AD, and 12.8% $F_1$ gain, 5.7% NMI gain, and 10.8% ARI gain on MTD. Code is available at https://github.com/HUST-SLOW/AnomalyNCD.
Authors: Jiaxin Lu, Yongqing Liang, Huijun Han, Jiacheng Hua, Junfeng Jiang, Xin Li, Qixing Huang
Abstract: Reconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. The reassembly problem requires understanding the attributes of individual pieces and establishing matches between different pieces. Many approaches also model priors of the underlying complete object. Existing approaches are tightly connected problems of shape segmentation, shape matching, and learning shape priors. We provide existing algorithms in this context and emphasize their similarities and differences to general-purpose approaches. We also survey the trends from early non-deep learning approaches to more recent deep learning approaches. In addition to algorithms, this survey will also describe existing datasets, open-source software packages, and applications. To the best of our knowledge, this is the first comprehensive survey on this topic in computer graphics.
Authors: Yanyi Zhang, Binglin Qiu, Qi Jia, Yu Liu, Ran He
Abstract: Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reason fine-grained compositionality of state-object pairs. To remedy this limitation, we propose a novel task called Compositional Incremental Learning (composition-IL), enabling the model to recognize state-object compositions as a whole in an incremental learning fashion. Since the lack of suitable benchmarks, we re-organize two existing datasets and make them tailored for composition-IL. Then, we propose a prompt-based Composition Incremental Learner (CompILer), to overcome the ambiguous composition boundary problem which challenges composition-IL largely. Specifically, we exploit multi-pool prompt learning, which is regularized by inter-pool prompt discrepancy and intra-pool prompt diversity. Besides, we devise object-injected state prompting by using object prompts to guide the selection of state prompts. Furthermore, we fuse the selected prompts by a generalized-mean strategy, to eliminate irrelevant information learned in the prompts. Extensive experiments on two datasets exhibit state-of-the-art performance achieved by CompILer.
Authors: Tianbin Li, Yanzhou Su, Wei Li, Bin Fu, Zhe Chen, Ziyan Huang, Guoan Wang, Chenglong Ma, Ying Chen, Ming Hu, Yanjun Li, Pengcheng Chen, Xiaowei Hu, Zhongying Deng, Yuanfeng Ji, Jin Ye, Yu Qiao, Junjun He
Abstract: Despite significant advancements in general AI, its effectiveness in the medical domain is limited by the lack of specialized medical knowledge. To address this, we formulate GMAI-VL-5.5M, a multimodal medical dataset created by converting hundreds of specialized medical datasets with various annotations into high-quality image-text pairs. This dataset offers comprehensive task coverage, diverse modalities, and rich image-text data. Building upon this dataset, we develop GMAI-VL, a general medical vision-language model, with a three-stage training strategy that enhances the integration of visual and textual information. This approach significantly improves the model's ability to process multimodal data, supporting accurate diagnoses and clinical decision-making. Experiments show that GMAI-VL achieves state-of-the-art performance across various multimodal medical tasks, including visual question answering and medical image diagnosis.
Authors: Zhening Liu, Yingdong Hu, Xinjie Zhang, Rui Song, Jiawei Shao, Zehong Lin, Jun Zhang
Abstract: The recent development of 3D Gaussian Splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction. Existing approaches mainly rely on full-length multi-view videos, while there has been limited exploration of online reconstruction methods that enable on-the-fly training and per-timestep streaming. Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians, thereby overlooking the difference between dynamic and static features as well as neglecting the temporal continuity in the scene. To address these limitations, we propose a novel three-stage pipeline for iterative streamable 4D dynamic spatial reconstruction. Our pipeline comprises a selective inheritance stage to preserve temporal continuity, a dynamics-aware shift stage to distinguish dynamic and static primitives and optimize their movements, and an error-guided densification stage to accommodate emerging objects. Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating the fastest on-the-fly training, superior representation quality, and real-time rendering capability. Project page: https://www.liuzhening.top/DASS
Authors: Su Sun, Cheng Zhao, Zhuoyang Sun, Yingjie Victor Chen, Mei Chen
Abstract: Most existing Dynamic Gaussian Splatting methods for complex dynamic urban scenarios rely on accurate object-level supervision from expensive manual labeling, limiting their scalability in real-world applications. In this paper, we introduce SplatFlow, a Self-Supervised Dynamic Gaussian Splatting within Neural Motion Flow Fields (NMFF) to learn 4D space-time representations without requiring tracked 3D bounding boxes, enabling accurate dynamic scene reconstruction and novel view RGB/depth/flow synthesis. SplatFlow designs a unified framework to seamlessly integrate time-dependent 4D Gaussian representation within NMFF, where NMFF is a set of implicit functions to model temporal motions of both LiDAR points and Gaussians as continuous motion flow fields. Leveraging NMFF, SplatFlow effectively decomposes static background and dynamic objects, representing them with 3D and 4D Gaussian primitives, respectively. NMFF also models the correspondences of each 4D Gaussian across time, which aggregates temporal features to enhance cross-view consistency of dynamic components. SplatFlow further improves dynamic object identification by distilling features from 2D foundation models into 4D space-time representation. Comprehensive evaluations conducted on the Waymo and KITTI Datasets validate SplatFlow's state-of-the-art (SOTA) performance for both image reconstruction and novel view synthesis in dynamic urban scenarios.
Authors: Wenhao Xu, Wenming Weng, Yueyi Zhang, Ruikang Xu, Zhiwei Xiong
Abstract: Deformable 3D Gaussian Splatting (3D-GS) is limited by missing intermediate motion information due to the low temporal resolution of RGB cameras. To address this, we introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction. We observe that threshold modeling for events plays a crucial role in achieving high-quality reconstruction. Therefore, we propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling. Moreover, we introduce a Dynamic-Static Decomposition strategy that first identifies dynamic areas by exploiting the inability of static Gaussians to represent motions, then applies a buffer-based soft decomposition to separate dynamic and static areas. This strategy accelerates rendering by avoiding unnecessary deformation in static areas, and focuses on dynamic areas to enhance fidelity. Additionally, we contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
Authors: Shuchen Weng, Haojie Zheng, Peixuan Zhan, Yuchen Hong, Han Jiang, Si Li, Boxin Shi
Abstract: We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment the diffusion transformer backbone with the sketch attention to interpret and inject fine-grained sketch semantics. A sketch-aware encoder ensures that repainted results are aligned with the provided sketch sequence. Additionally, we contribute the VireSet, a dataset with detailed annotations tailored for training and evaluating video instance editing methods. Experimental results demonstrate the effectiveness of VIRES, which outperforms state-of-the-art methods in visual quality, temporal consistency, condition alignment, and human ratings. Project page: https://hjzheng.net/projects/VIRES/
Authors: Mohamed Aghzal, Xiang Yue, Erion Plaku, Ziyu Yao
Abstract: Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the planning framework as a helpful plan evaluator? In this work, we generalize this question to consider LLMs augmented with visual understanding, i.e., Vision-Language Models (VLMs). We introduce PathEval, a novel benchmark evaluating VLMs as plan evaluators in complex path-planning scenarios. Succeeding in the benchmark requires a VLM to be able to abstract traits of optimal paths from the scenario description, demonstrate precise low-level perception on each path, and integrate this information to decide the better path. Our analysis of state-of-the-art VLMs reveals that these models face significant challenges on the benchmark. We observe that the VLMs can precisely abstract given scenarios to identify the desired traits and exhibit mixed performance in integrating the provided information. Yet, their vision component presents a critical bottleneck, with models struggling to perceive low-level details about a path. Our experimental results show that this issue cannot be trivially addressed via end-to-end fine-tuning; rather, task-specific discriminative adaptation of these vision encoders is needed for these VLMs to become effective path evaluators.
Authors: S\"onke Tenckhoff, Mario Koddenbrock, Erik Rodner
Abstract: Automated object detection has become increasingly valuable across diverse applications, yet efficient, high-quality annotation remains a persistent challenge. In this paper, we present the development and evaluation of a platform designed to interactively improve object detection models. The platform allows uploading and annotating images as well as fine-tuning object detection models. Users can then manually review and refine annotations, further creating improved snapshots that are used for automatic object detection on subsequent image uploads - a process we refer to as semi-automatic annotation resulting in a significant gain in annotation efficiency. Whereas iterative refinement of model results to speed up annotation has become common practice, we are the first to quantitatively evaluate its benefits with respect to time, effort, and interaction savings. Our experimental results show clear evidence for a significant time reduction of up to 53% for semi-automatic compared to manual annotation. Importantly, these efficiency gains did not compromise annotation quality, while matching or occasionally even exceeding the accuracy of manual annotations. These findings demonstrate the potential of our lightweight annotation platform for creating high-quality object detection datasets and provide best practices to guide future development of annotation platforms. The platform is open-source, with the frontend and backend repositories available on GitHub. To support the understanding of our labeling process, we have created an explanatory video demonstrating the methodology using microscopy images of E. coli bacteria as an example.
Authors: Duo Zheng, Shijia Huang, Liwei Wang
Abstract: The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to enhance MLLMs, such as incorporating point cloud features, have been made, yet a considerable gap remains between the models' learned representations and the inherent complexity of 3D scenes. This discrepancy largely stems from the training of MLLMs on predominantly 2D data, which restricts their effectiveness in comprehending 3D spaces. To address this issue, in this paper, we propose a novel generalist model, i.e., Video-3D LLM, for 3D scene understanding. By treating 3D scenes as dynamic videos and incorporating 3D position encoding into these representations, our Video-3D LLM aligns video representations with real-world spatial contexts more accurately. In addition, we have implemented a maximum coverage sampling technique to optimize the trade-off between computational cost and performance. Extensive experiments demonstrate that our model achieves state-of-the-art performance on several 3D scene understanding benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.
Authors: Yizhou Wang, Tim Meinhardt, Orcun Cetintas, Cheng-Yen Yang, Sameer Satish Pusegaonkar, Benjamin Missaoui, Sujit Biswas, Zheng Tang, Laura Leal-Taix\'e
Abstract: Object perception from multi-view cameras is crucial for intelligent systems, particularly in indoor environments, e.g., warehouses, retail stores, and hospitals. Most traditional multi-target multi-camera (MTMC) detection and tracking methods rely on 2D object detection, single-view multi-object tracking (MOT), and cross-view re-identification (ReID) techniques, without properly handling important 3D information by multi-view image aggregation. In this paper, we propose a 3D object detection and tracking framework, named MCBLT, which first aggregates multi-view images with necessary camera calibration parameters to obtain 3D object detections in bird's-eye view (BEV). Then, we introduce hierarchical graph neural networks (GNNs) to track these 3D detections in BEV for MTMC tracking results. Unlike existing methods, MCBLT has impressive generalizability across different scenes and diverse camera settings, with exceptional capability for long-term association handling. As a result, our proposed MCBLT establishes a new state-of-the-art on the AICity'24 dataset with $81.22$ HOTA, and on the WildTrack dataset with $95.6$ IDF1.
Authors: Nitish Mital, Simon Malzard, Richard Walters, Celso M. De Melo, Raghuveer Rao, Victoria Nockles
Abstract: Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear how to design synthetic training data to optimally improve model performance (e.g, whether and where to introduce more realism or more abstraction) and 2) the domain expertise, time and effort required from human operators for this design and optimisation process represents a major practical challenge. Here we propose a novel conceptual approach to improve the efficiency of designing synthetic images, by using robust Explainable AI (XAI) techniques to guide a human-in-the-loop process of modifying 3D mesh models used to generate these images. Importantly, this framework allows both modifications that increase and decrease realism in synthetic data, which can both improve model performance. We illustrate this concept using a real-world example where data are sparse; detection of vehicles in infrared imagery. We fine-tune an initial YOLOv8 model on the ATR DSIAC infrared dataset and synthetic images generated from 3D mesh models in the Unity gaming engine, and then use XAI saliency maps to guide modification of our Unity models. We show that synthetic data can improve detection of vehicles in orientations unseen in training by 4.6% (to mAP50 = 94.6%). We further improve performance by an additional 1.5% (to 96.1%) through our new XAI-guided approach, which reduces misclassifications through both increasing and decreasing the realism of different parts of the synthetic data. Our proof-of-concept results pave the way for fine, XAI-controlled curation of synthetic datasets tailored to improve object detection performance, whilst simultaneously reducing the burden on human operators in designing and optimising these datasets.
Authors: Caixin Kang, Yubo Chen, Shouwei Ruan, Shiji Zhao, Ruochen Zhang, Jiayi Wang, Shan Fu, Xingxing Wei
Abstract: With the rise of deep learning, facial recognition technology has seen extensive research and rapid development. Although facial recognition is considered a mature technology, we find that existing open-source models and commercial algorithms lack robustness in certain complex Out-of-Distribution (OOD) scenarios, raising concerns about the reliability of these systems. In this paper, we introduce OODFace, which explores the OOD challenges faced by facial recognition models from two perspectives: common corruptions and appearance variations. We systematically design 30 OOD scenarios across 9 major categories tailored for facial recognition. By simulating these challenges on public datasets, we establish three robustness benchmarks: LFW-C/V, CFP-FP-C/V, and YTF-C/V. We then conduct extensive experiments on 19 facial recognition models and 3 commercial APIs, along with extended physical experiments on face masks to assess their robustness. Next, we explore potential solutions from two perspectives: defense strategies and Vision-Language Models (VLMs). Based on the results, we draw several key insights, highlighting the vulnerability of facial recognition systems to OOD data and suggesting possible solutions. Additionally, we offer a unified toolkit that includes all corruption and variation types, easily extendable to other datasets. We hope that our benchmarks and findings can provide guidance for future improvements in facial recognition model robustness.
Authors: Dean Hazineh, Federico Capasso, Todd Zickler
Abstract: We consider the problem of reconstructing a HxWx31 hyperspectral image from a HxW grayscale snapshot measurement that is captured using only a single diffractive optic and a filterless panchromatic photosensor. This problem is severely ill-posed, but we present the first model that produces high-quality results. We make efficient use of limited data by training a conditional denoising diffusion model that operates on small patches in a shift-invariant manner. During inference, we synchronize per-patch hyperspectral predictions using guidance derived from the optical point spread function. Surprisingly, our experiments reveal that patch sizes as small as the PSFs support achieve excellent results, and they show that local optical cues are sufficient to capture full spectral information. Moreover, by drawing multiple samples, our model provides per-pixel uncertainty estimates that strongly correlate with reconstruction error. Our work lays the foundation for a new class of high-resolution snapshot hyperspectral imagers that are compact and light-efficient.
Authors: Xiaofeng Tan, Hongsong Wang, Xin Geng, Liang Wang
Abstract: Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. However, these methods struggle with two key limitations: (1) insufficient robustness in open-set scenarios, where unseen normal motions are frequently misclassified as anomalies, and (2) an overemphasis on, but restricted capacity for, local motion reconstruction, which are inherently difficult to capture accurately due to their diversity. To overcome these challenges, we introduce a novel frequency-guided diffusion model with perturbation training. First, we enhance robustness by training a generator to produce perturbed samples, which are similar to normal samples and target the weakness of the reconstruction model. This training paradigm expands the reconstruction domain of the model, improving its generalization to unseen normal motions. Second, to address the overemphasis on motion details, we employ the 2D Discrete Cosine Transform (DCT) to separate high-frequency (local) and low-frequency (global) motion components. By guiding the diffusion model with observed high-frequency information, we prioritize the reconstruction of low-frequency components, enabling more accurate and robust anomaly detection. Extensive experiments on five widely used VAD datasets demonstrate that our approach surpasses state-of-the-art methods, underscoring its effectiveness in open-set scenarios and diverse motion contexts. Our project website is https://xiaofeng-tan.github.io/projects/FG-Diff/index.html.
URLs: https://xiaofeng-tan.github.io/projects/FG-Diff/index.html.
Authors: Marcin Przewi\k{e}\'zlikowski, Randall Balestriero, Wojciech Jasi\'nski, Marek \'Smieja, Bartosz Zieli\'nski
Abstract: Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typically inferior to competing approaches. Most users cannot afford fine-tuning due to the need for large amounts of data, high GPU consumption, and specialized user knowledge. Therefore, the practical use of MIM representations is limited. In this paper we ask what is the reason for the poor out-of-the-box performance of MIMs. Is it due to weaker features produced by MIM models, or is it due to suboptimal usage? Through detailed analysis, we show that attention in MIMs is spread almost uniformly over many patches, leading to ineffective aggregation by the [cls] token. Based on this insight, we propose Selective Aggregation to better capture the rich semantic information retained in patch tokens, which significantly improves the out-of-the-box performance of MIM.
Authors: Jingzhi Li, Zongwei Wu, Eduard Zamfir, Radu Timofte
Abstract: Accurate 3D objects relighting in diverse unseen environments is crucial for realistic virtual object placement. Due to the albedo-lighting ambiguity, existing methods often fall short in producing faithful relights. Without proper constraints, observed training views can be explained by numerous combinations of lighting and material attributes, lacking physical correspondence with the actual environment maps used for relighting. In this work, we present ReCap, treating cross-environment captures as multi-task target to provide the missing supervision that cuts through the entanglement. Specifically, ReCap jointly optimizes multiple lighting representations that share a common set of material attributes. This naturally harmonizes a coherent set of lighting representations around the mutual material attributes, exploiting commonalities and differences across varied object appearances. Such coherence enables physically sound lighting reconstruction and robust material estimation - both essential for accurate relighting. Together with a streamlined shading function and effective post-processing, ReCap outperforms all leading competitors on an expanded relighting benchmark.
Authors: Alexander Pondaven, Aliaksandr Siarohin, Sergey Tulyakov, Philip Torr, Fabio Pizzati
Abstract: We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embeddings, granting us a boost in zero-shot motion transfer capabilities. We evaluate DiTFlow against recently published methods, outperforming all across multiple metrics and human evaluation.
Authors: Mingkun Lei, Xue Song, Beier Zhu, Hao Wang, Chi Zhang
Abstract: Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges remain, particularly with overfitting to reference styles, limiting stylistic control, and misaligning with textual content. In this paper, we propose three complementary strategies to address these issues. First, we introduce a cross-modal Adaptive Instance Normalization (AdaIN) mechanism for better integration of style and text features, enhancing alignment. Second, we develop a Style-based Classifier-Free Guidance (SCFG) approach that enables selective control over stylistic elements, reducing irrelevant influences. Finally, we incorporate a teacher model during early generation stages to stabilize spatial layouts and mitigate artifacts. Our extensive evaluations demonstrate significant improvements in style transfer quality and alignment with textual prompts. Furthermore, our approach can be integrated into existing style transfer frameworks without fine-tuning.
Authors: Ayaka Higami, Karin Oshima, Tomoyo Isoguchi Shiramatsu, Hirokazu Takahashi, Shohei Nobuhara, Ko Nishino
Abstract: Analyzing rat behavior lies at the heart of many scientific studies. Past methods for automated rodent modeling have focused on 3D pose estimation from keypoints, e.g., face and appendages. The pose, however, does not capture the rich body surface movement encoding the subtle rat behaviors like curling and stretching. The body surface lacks features that can be visually defined, evading these established keypoint-based methods. In this paper, we introduce the first method for reconstructing the rat body surface as a dense set of points by learning to predict it from the sparse keypoints that can be detected with past methods. Our method consists of two key contributions. The first is RatDome, a novel multi-camera system for rat behavior capture, and a large-scale dataset captured with it that consists of pairs of 3D keypoints and 3D body surface points. The second is RatBodyFormer, a novel network to transform detected keypoints to 3D body surface points. RatBodyFormer is agnostic to the exact locations of the 3D body surface points in the training data and is trained with masked-learning. We experimentally validate our framework with a number of real-world experiments. Our results collectively serve as a novel foundation for automated rat behavior analysis.
Authors: Jiaying Lin, Shuquan Ye, Rynson W. H. Lau
Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive results on various vision tasks, leveraging recent advancements in large language models. However, a critical question remains unaddressed: do MLLMs perceive visual information similarly to humans? Current benchmarks lack the ability to evaluate MLLMs from this perspective. To address this challenge, we introduce HVSBench, a large-scale benchmark designed to assess the alignment between MLLMs and the human visual system (HVS) on fundamental vision tasks that mirror human vision. HVSBench curated over 85K multimodal samples, spanning 13 categories and 5 fields in HVS, including Prominence, Subitizing, Prioritizing, Free-Viewing, and Searching. Extensive experiments demonstrate the effectiveness of our benchmark in providing a comprehensive evaluation of MLLMs. Specifically, we evaluate 13 MLLMs, revealing that even the best models show significant room for improvement, with most achieving only moderate results. Our experiments reveal that HVSBench presents a new and significant challenge for cutting-edge MLLMs. Diverse human participants attained strong performance, significantly outperforming MLLMs, which further underscores the benchmark's high quality. We believe that HVSBench will facilitate research on human-aligned and explainable MLLMs, marking a key step in understanding how MLLMs perceive and process visual information.
Authors: Yunxiang Fu, Meng Lou, Yizhou Yu
Abstract: High-quality semantic segmentation relies on three key capabilities: global context modeling, local detail encoding, and multi-scale feature extraction. However, recent methods struggle to possess all these capabilities simultaneously. Hence, we aim to empower segmentation networks to simultaneously carry out efficient global context modeling, high-quality local detail encoding, and rich multi-scale feature representation for varying input resolutions. In this paper, we introduce SegMAN, a novel linear-time model comprising a hybrid feature encoder dubbed SegMAN Encoder, and a decoder based on state space models. Specifically, the SegMAN Encoder synergistically integrates sliding local attention with dynamic state space models, enabling highly efficient global context modeling while preserving fine-grained local details. Meanwhile, the MMSCopE module in our decoder enhances multi-scale context feature extraction and adaptively scales with the input resolution. Our SegMAN-B Encoder achieves 85.1% ImageNet-1k accuracy (+1.5% over VMamba-S with fewer parameters). When paired with our decoder, the full SegMAN-B model achieves 52.6% mIoU on ADE20K (+1.6% over SegNeXt-L with 15% fewer GFLOPs), 83.8% mIoU on Cityscapes (+2.1% over SegFormer-B3 with half the GFLOPs), and 1.6% higher mIoU than VWFormer-B3 on COCO-Stuff with lower GFLOPs. Our code is available at https://github.com/yunxiangfu2001/SegMAN.
Authors: Tao Xie, Xi Chen, Zhen Xu, Yiman Xie, Yudong Jin, Yujun Shen, Sida Peng, Hujun Bao, Xiaowei Zhou
Abstract: Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU's RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis. The code is available at https://zju3dv.github.io/envgs.
Authors: Suyoung Lee, Jaeyoung Chung, Kihoon Kim, Jaeyoo Huh, Gunhee Lee, Minsoo Lee, Kyoung Mu Lee
Abstract: Feed-forward 3D Gaussian splatting (3DGS) models have gained significant popularity due to their ability to generate scenes immediately without needing per-scene optimization. Although omnidirectional images are becoming more popular since they reduce the computation required for image stitching to composite a holistic scene, existing feed-forward models are only designed for perspective images. The unique optical properties of omnidirectional images make it difficult for feature encoders to correctly understand the context of the image and make the Gaussian non-uniform in space, which hinders the image quality synthesized from novel views. We propose OmniSplat, a training-free fast feed-forward 3DGS generation framework for omnidirectional images. We adopt a Yin-Yang grid and decompose images based on it to reduce the domain gap between omnidirectional and perspective images. The Yin-Yang grid can use the existing CNN structure as it is, but its quasi-uniform characteristic allows the decomposed image to be similar to a perspective image, so it can exploit the strong prior knowledge of the learned feed-forward network. OmniSplat demonstrates higher reconstruction accuracy than existing feed-forward networks trained on perspective images. Our project page is available on: https://robot0321.github.io/omnisplat/index.html.
Authors: Haoran You, Connelly Barnes, Yuqian Zhou, Yan Kang, Zhenbang Du, Wei Zhou, Lingzhi Zhang, Yotam Nitzan, Xiaoyang Liu, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Yingyan Celine Lin
Abstract: Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency bottleneck is that existing DiTs apply equal computation across all regions of an image. However, not all image tokens are equally important, and certain localized areas require more computation, such as objects. To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically route computation across layers and timesteps for each image token, resulting in efficient DiTs. Specifically, DiffCR integrates three features: (1) A token-level routing scheme where each DiT layer includes a router that is fine-tuned jointly with model weights to predict token importance scores. In this way, unimportant tokens bypass the entire layer's computation; (2) A layer-wise differentiable ratio mechanism where different DiT layers automatically learn varying compression ratios from a zero initialization, resulting in large compression ratios in redundant layers while others remain less compressed or even uncompressed; (3) A timestep-wise differentiable ratio mechanism where each denoising timestep learns its own compression ratio. The resulting pattern shows higher ratios for noisier timesteps and lower ratios as the image becomes clearer. Extensive experiments on text-to-image and inpainting tasks show that DiffCR effectively captures dynamism across token, layer, and timestep axes, achieving superior trade-offs between generation quality and efficiency compared to prior works. The project website is available at https://www.haoranyou.com/diffcr.
Authors: Jinhui Yi, Syed Talal Wasim, Yanan Luo, Muzammal Naseer, Juergen Gall
Abstract: We present an efficient encoder-free approach for video-language understanding that achieves competitive performance while significantly reducing computational overhead. Current video-language models typically rely on heavyweight image encoders (300M-1.1B parameters) or video encoders (1B-1.4B parameters), creating a substantial computational burden when processing multi-frame videos. Our method introduces a novel Spatio-Temporal Alignment Block (STAB) that directly processes video inputs without requiring pre-trained encoders while using only 45M parameters for visual processing - at least a 6.5$\times$ reduction compared to traditional approaches. The STAB architecture combines Local Spatio-Temporal Encoding for fine-grained feature extraction, efficient spatial downsampling through learned attention and separate mechanisms for modeling frame-level and video-level relationships. Our model achieves comparable or superior performance to encoder-based approaches for open-ended video question answering on standard benchmarks. The fine-grained video question-answering evaluation demonstrates our model's effectiveness, outperforming the encoder-based approaches Video-ChatGPT and Video-LLaVA in key aspects like correctness and temporal understanding. Extensive ablation studies validate our architectural choices and demonstrate the effectiveness of our spatio-temporal modeling approach while achieving 3-4$\times$ faster processing speeds than previous methods. Code is available at https://jh-yi.github.io/Video-Panda.
Authors: Wenkun He, Yun Liu, Ruitao Liu, Li Yi
Abstract: Synthesizing realistic human-object interaction motions is a critical problem in VR/AR and human animation. Unlike the commonly studied scenarios involving a single human or hand interacting with one object, we address a more generic multi-body setting with arbitrary numbers of humans, hands, and objects. This complexity introduces significant challenges in synchronizing motions due to the high correlations and mutual influences among bodies. To address these challenges, we introduce SyncDiff, a novel method for multi-body interaction synthesis using a synchronized motion diffusion strategy. SyncDiff employs a single diffusion model to capture the joint distribution of multi-body motions. To enhance motion fidelity, we propose a frequency-domain motion decomposition scheme. Additionally, we introduce a new set of alignment scores to emphasize the synchronization of different body motions. SyncDiff jointly optimizes both data sample likelihood and alignment likelihood through an explicit synchronization strategy. Extensive experiments across four datasets with various multi-body configurations demonstrate the superiority of SyncDiff over existing state-of-the-art motion synthesis methods.
Authors: Chun-Hao Paul Huang, Niloy Mitra, Hyeonho Jeong, Jae Shin Yoon, Duygu Ceylan
Abstract: Emergent capabilities of image generators have led to many impactful zero- or few-shot applications. Inspired by this success, we investigate whether video generators similarly exhibit 3D-awareness. Using structure-from-motion as a 3D-aware task, we test if intermediate features of a video generator - OpenSora in our case - can support camera pose estimation. Surprisingly, at first, we only find a weak correlation between the two tasks. Deeper investigation reveals that although the video generator produces plausible video frames, the frames themselves are not truly 3D-consistent. Instead, we propose to jointly train for the two tasks, using photometric generation and 3D aware errors. Specifically, we find that SoTA video generation and camera pose estimation (i.e.,DUSt3R [79]) networks share common structures, and propose an architecture that unifies the two. The proposed unified model, named \nameMethod, produces camera pose estimates with competitive quality while producing 3D-consistent videos. In summary, we propose the first unified video generator that is 3D-consistent, generates realistic video frames, and can potentially be repurposed for other 3D-aware tasks.
Authors: Huaxiang Zhang, Kai Liu, Zhongxue Gan, Guo-Niu Zhu
Abstract: Unmanned aerial vehicle object detection (UAV-OD) has been widely used in various scenarios. However, most existing UAV-OD algorithms rely on manually designed components, which require extensive tuning. End-to-end models that do not depend on such manually designed components are mainly designed for natural images, which are less effective for UAV imagery. To address such challenges, this paper proposes an efficient detection transformer (DETR) framework tailored for UAV imagery, i.e., UAV-DETR. The framework includes a multi-scale feature fusion with frequency enhancement module, which captures both spatial and frequency information at different scales. In addition, a frequency-focused down-sampling module is presented to retain critical spatial details during down-sampling. A semantic alignment and calibration module is developed to align and fuse features from different fusion paths. Experimental results demonstrate the effectiveness and generalization of our approach across various UAV imagery datasets. On the VisDrone dataset, our method improves AP by 3.1\% and $\text{AP}_{50}$ by 4.2\% over the baseline. Similar enhancements are observed on the UAVVaste dataset. The project page: https://github.com/ValiantDiligent/UAV-DETR
Authors: Felix Krause, Timy Phan, Ming Gui, Stefan Andreas Baumann, Vincent Tao Hu, Bj\"orn Ommer
Abstract: Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and personalization were quickly adopted by the community. However, training these models in the first place remains very costly. While several recent approaches - including masking, distillation, and architectural modifications - have been proposed to improve training efficiency, each of these methods comes with a tradeoff: they achieve enhanced performance at the expense of increased computational cost or vice versa. In contrast, this work aims to improve training efficiency as well as generative performance at the same time through routes that act as a transport mechanism for randomly selected tokens from early layers to deeper layers of the model. Our method is not limited to the common transformer-based model - it can also be applied to state-space models and achieves this without architectural modifications or additional parameters. Finally, we show that TREAD reduces computational cost and simultaneously boosts model performance on the standard ImageNet-256 benchmark in class-conditional synthesis. Both of these benefits multiply to a convergence speedup of 14x at 400K training iterations compared to DiT and 37x compared to the best benchmark performance of DiT at 7M training iterations. Furthermore, we achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting, which improves upon the DiT, without architectural changes.
Authors: Rujie Wu, Xiaojian Ma, Hai Ci, Yue Fan, Yuxuan Wang, Haozhe Zhao, Qing Li, Yizhou Wang
Abstract: This paper introduces LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We propose a systematic approach that organizes videos into a hierarchical tree structure for QA generation and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.)). We also offer explicit timestamp annotations of relevant events for each QA pair. We have conducted extensive human studies on LongViTU, and the results prove the quality of our dataset. To better evaluate the challenges posed by LongViTU's emphasis on long-term context and condensed reasoning, we manually curate a subset of LongViTU into a benchmark. Evaluations using a state-of-the-art open-source model (LongVU), a proprietary model (Gemini-1.5-Pro), and human annotators yield GPT-4 scores of 49.9, 52.3, and 81.0, respectively, underscoring the substantial difficulty presented by LongViTU questions. Performing supervised fine-tuning (SFT) of LongVU and LLaVA-Video on LongViTU data results in average performance gains of 2.5% and 3.7%, respectively, across a suite of long video understanding benchmarks (EgoSchema, VideoMME-Long, MLVU, LVBench).
Authors: Yifei Li, Junbo Niu, Ziyang Miao, Chunjiang Ge, Yuanhang Zhou, Qihao He, Xiaoyi Dong, Haodong Duan, Shuangrui Ding, Rui Qian, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang
Abstract: Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of nine Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with online video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://github.com/JoeLeelyf/OVO-Bench.
Authors: Jiuling Zhang
Abstract: Monocular Depth Estimation (MDE) is fundamental to computer vision, enabling spatial understanding, 3D reconstruction, and autonomous driving. Deep learning-based MDE predicts relative depth from a single image, but the lack of metric scale introduces inconsistencies, limiting applicability in tasks such as visual SLAM, 3D reconstruction, and novel view synthesis. Monocular Metric Depth Estimation (MMDE) overcomes this limitation by enabling precise scene-scale inference, improving depth consistency, enhancing stability in sequential tasks, and streamlining integration into practical systems. This paper systematically reviews the evolution of depth estimation, from traditional geometric methods to deep learning breakthroughs, emphasizing scale-agnostic approaches in zero-shot generalization which is crucial for advancing MMDE. Recent progress in zero-shot MMDE is examined, focusing on challenges such as model generalization and boundary detail loss. To address these issues, researchers have explored unlabeled data augmentation, image patching, architectural optimization, and generative techniques. This review analyzes these developments, assessing their impact and limitations. Key findings are synthesized, unresolved challenges outlined, and future research direction proposal. By providing a clear technical roadmap and insight into emerging trends, this work aims to drive innovation and expand the real-world applications of MMDE.
Authors: Yuliang Gu, Weilun Tsao, Bo Du, Thierry G\'eraud, Yongchao Xu
Abstract: Annotating 3D medical images demands substantial time and expertise, driving the adoption of semi-supervised learning (SSL) for segmentation tasks. However, the complex anatomical structures of organs often lead to significant class imbalances, posing major challenges for deploying SSL in real-world scenarios. Despite the availability of valuable prior information, such as inter-organ relative positions and organ shape priors, existing SSL methods have yet to fully leverage these insights. To address this gap, we propose a novel approach that integrates textual anatomical knowledge (TAK) into the segmentation model. Specifically, we use GPT-4o to generate textual descriptions of anatomical priors, which are then encoded using a CLIP-based model. These encoded priors are injected into the segmentation model as parameters of the segmentation head. Additionally, contrastive learning is employed to enhance the alignment between textual priors and visual features. Extensive experiments demonstrate the superior performance of our method, significantly surpassing state-of-the-art approaches. The source code will be available at: https://github.com/Lunn88/TAK-Semi.
Authors: Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa
Abstract: Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision.
Authors: Goodarz Mehr, Azim Eskandarian
Abstract: Bird's-eye view (BEV) perception has garnered significant attention in autonomous driving in recent years, in part because BEV representation facilitates multi-modal sensor fusion. BEV representation enables a variety of perception tasks including BEV segmentation, a concise view of the environment useful for planning a vehicle's trajectory. However, this representation is not fully supported by existing datasets, and creation of new datasets for this purpose can be a time-consuming endeavor. To address this challenge, we introduce SimBEV. SimBEV is a randomized synthetic data generation tool that is extensively configurable and scalable, supports a wide array of sensors, incorporates information from multiple sources to capture accurate BEV ground truth, and enables a variety of perception tasks including BEV segmentation and 3D object detection. SimBEV is used to create the SimBEV dataset, a large collection of annotated perception data from diverse driving scenarios. SimBEV and the SimBEV dataset are open and available to the public.
Authors: Sihwan Park, Doohyuk Jang, Sungyub Kim, Souvik Kundu, Eunho Yang
Abstract: Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection ambiguity, where multiple tokens share similarly low probabilities and thus reduce acceptance rates. Recently, relaxed speculative decoding with dynamic tree drafting was proposed to mitigate this ambiguity, demonstrating promising results in accelerating visual AR models. However, we observe that token selection ambiguity still negatively affects dynamic tree drafting, resulting in shallow draft trees and limited acceleration. To overcome this issue, we introduce LANTERN++, a refined framework that integrates static tree drafting with a tailored relaxed acceptance condition, allowing drafts to be selected independently of low-confidence predictions. This enables the acceptance of deeper sequences, improving decoding efficiency while preserving image quality. Extensive experiments on state-of-the-art visual AR models demonstrate that LANTERN++ significantly accelerates inference, achieving up to $\mathbf{\times 2.56}$ speedup over standard AR decoding while maintaining high image quality. The code is publicly available at https://github.com/jadohu/LANTERN.
Authors: Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, Yan-Pei Cao
Abstract: Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
Authors: Giorgos Kordopatis-Zilos, Vladan Stojni\'c, Anna Manko, Pavel \v{S}uma, Nikolaos-Antonios Ypsilantis, Nikos Efthymiadis, Zakaria Laskar, Ji\v{r}\'i Matas, Ond\v{r}ej Chum, Giorgos Tolias
Abstract: This work introduces ILIAS, a new test dataset for Instance-Level Image retrieval At Scale. It is designed to evaluate the ability of current and future foundation models and retrieval techniques to recognize particular objects. The key benefits over existing datasets include large scale, domain diversity, accurate ground truth, and a performance that is far from saturated. ILIAS includes query and positive images for 1,000 object instances, manually collected to capture challenging conditions and diverse domains. Large-scale retrieval is conducted against 100 million distractor images from YFCC100M. To avoid false negatives without extra annotation effort, we include only query objects confirmed to have emerged after 2014, i.e. the compilation date of YFCC100M. An extensive benchmarking is performed with the following observations: i) models fine-tuned on specific domains, such as landmarks or products, excel in that domain but fail on ILIAS ii) learning a linear adaptation layer using multi-domain class supervision results in performance improvements, especially for vision-language models iii) local descriptors in retrieval re-ranking are still a key ingredient, especially in the presence of severe background clutter iv) the text-to-image performance of the vision-language foundation models is surprisingly close to the corresponding image-to-image case. website: https://vrg.fel.cvut.cz/ilias/
Authors: Guanqi Zhan, Yuanpei Liu, Kai Han, Weidi Xie, Andrew Zisserman
Abstract: The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for text-to-image re-ranking. The approach, Enhanced Language-Image Pre-training (ELIP), uses the text query, via a simple MLP mapping network, to predict a set of visual prompts to condition the ViT image encoding. ELIP can easily be applied to the commonly used CLIP, SigLIP and BLIP-2 networks. To train the architecture with limited computing resources, we develop a 'student friendly' best practice, involving global hard sample mining, and curation of a large-scale dataset. On the evaluation side, we set up two new out-of-distribution (OOD) benchmarks, Occluded COCO and ImageNet-R, to assess the zero-shot generalisation of the models to different domains. The results demonstrate that ELIP significantly boosts CLIP/SigLIP/SigLIP-2 text-to-image retrieval performance and outperforms BLIP-2 on several benchmarks, as well as providing an easy means to adapt to OOD datasets.
Authors: Kai Hu, Feng Gao, Xiaohan Nie, Peng Zhou, Son Tran, Tal Neiman, Lingyun Wang, Mubarak Shah, Raffay Hamid, Bing Yin, Trishul Chilimbi
Abstract: Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply naive uniform sampling to reduce the number of video frames that are fed into an M-LLM, particularly for long context videos. However, it could lose crucial context in certain periods of a video, so that the downstream M-LLM may not have sufficient visual information to answer a question. To attack this pain point, we propose a light-weight M-LLM -based frame selection method that adaptively select frames that are more relevant to users' queries. In order to train the proposed frame selector, we introduce two supervision signals (i) Spatial signal, where single frame importance score by prompting a M-LLM; (ii) Temporal signal, in which multiple frames selection by prompting Large Language Model (LLM) using the captions of all frame candidates. The selected frames are then digested by a frozen downstream video M-LLM for visual reasoning and question answering. Empirical results show that the proposed M-LLM video frame selector improves the performances various downstream video Large Language Model (video-LLM) across medium (ActivityNet, NExT-QA) and long (EgoSchema, LongVideoBench) context video question answering benchmarks.
Authors: Juil Koo, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Minhyuk Sung
Abstract: Generative methods for image and video editing use generative models as priors to perform edits despite incomplete information, such as changing the composition of 3D objects shown in a single image. Recent methods have shown promising composition editing results in the image setting, but in the video setting, editing methods have focused on editing object's appearance and motion, or camera motion, and as a result, methods to edit object composition in videos are still missing. We propose \name as a method for editing 3D object compositions in videos of static scenes with camera motion. Our approach allows editing the 3D position of a 3D object across all frames of a video in a temporally consistent manner. This is achieved by lifting intermediate features of a generative model to a 3D reconstruction that is shared between all frames, editing the reconstruction, and projecting the features on the edited reconstruction back to each frame. To the best of our knowledge, this is the first generative approach to edit object compositions in videos. Our approach is simple and training-free, while outperforming state-of-the-art image editing baselines.
Authors: Fangming Cui, Yonggang Zhang, Xuan Wang, Xule Wang, Liang Xiao
Abstract: Existing vision-language models (VLMs) such as CLIP have showcased an impressive capability to generalize well across various downstream tasks. These models leverage the synergy between visual and textual information, enabling them to understand and reason about the content present in images and text in a unified manner. This article provides a brief overview of CLIP based on few-shot prompt learning, including experimental data and technical characteristics of some methods. The purpose of this review is to provide a reference for researchers who have just started their research in generalizable prompting of CLIP through few-shot training for classification across 15 datasets and also to facilitate the integration of this field by researchers in other downstream tasks.
Authors: Theodore Zhao, Sid Kiblawi, Naoto Usuyama, Ho Hin Lee, Sam Preston, Hoifung Poon, Mu Wei
Abstract: Detecting and segmenting small objects, such as lung nodules and tumor lesions, remains a critical challenge in image analysis. These objects often occupy less than 0.1% of an image, making traditional transformer architectures inefficient and prone to performance degradation due to redundant attention computations on irrelevant regions. Existing sparse attention mechanisms rely on rigid hierarchical structures, which are poorly suited for detecting small, variable, and uncertain object locations. In this paper, we propose BoltzFormer, a novel transformer-based architecture designed to address these challenges through dynamic sparse attention. BoltzFormer identifies and focuses attention on relevant areas by modeling uncertainty using a Boltzmann distribution with an annealing schedule. Initially, a higher temperature allows broader area sampling in early layers, when object location uncertainty is greatest. As the temperature decreases in later layers, attention becomes more focused, enhancing efficiency and accuracy. BoltzFormer seamlessly integrates into existing transformer architectures via a modular Boltzmann attention sampling mechanism. Comprehensive evaluations on benchmark datasets demonstrate that BoltzFormer significantly improves segmentation performance for small objects while reducing attention computation by an order of magnitude compared to previous state-of-the-art methods.
Authors: Nianzu Yang, Pandeng Li, Liming Zhao, Yang Li, Chen-Wei Xie, Yehui Tang, Xudong Lu, Zhihang Liu, Yun Zheng, Yu Liu, Junchi Yan
Abstract: Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage training tricks that go beyond basic reconstruction loss and KL regularization. Among these tricks, the most challenging is the precise tuning of adversarial training with additional Generative Adversarial Networks (GANs) in the final stage, which can hinder stable convergence. In contrast to GANs, diffusion models offer more stable training processes and can generate higher-quality results. Inspired by these advantages, we propose CDT, a novel Conditioned Diffusion-based video Tokenizer, that replaces the GAN-based decoder with a conditional causal diffusion model. The encoder compresses spatio-temporal information into compact latents, while the decoder reconstructs videos through a reverse diffusion process conditioned on these latents. During inference, we incorporate a feature cache mechanism to generate videos of arbitrary length while maintaining temporal continuity and adopt sampling acceleration technique to enhance efficiency. Trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch, extensive experiments demonstrate that CDT achieves state-of-the-art performance in video reconstruction tasks with just a single-step sampling. Even a scaled-down version of CDT (3$\times$ inference speedup) still performs comparably with top baselines. Moreover, the latent video generation model trained with CDT also exhibits superior performance. The source code and pretrained weights are available at https://github.com/ali-vilab/CDT.
Authors: Shuhe Wang, Xiaoya Li, Jiwei Li, Guoyin Wang, Xiaofei Sun, Bob Zhu, Han Qiu, Mo Yu, Shengjie Shen, Tianwei Zhang, Eduard Hovy
Abstract: Due to the data-driven nature of current face identity (FaceID) customization methods, all state-of-the-art models rely on large-scale datasets containing millions of high-quality text-image pairs for training. However, none of these datasets are publicly available, which restricts transparency and hinders further advancements in the field. To address this issue, in this paper, we collect and release FaceID-6M, the first large-scale, open-source FaceID dataset containing 6 million high-quality text-image pairs. Filtered from LAION-5B \cite{schuhmann2022laion}, FaceID-6M undergoes a rigorous image and text filtering steps to ensure dataset quality, including resolution filtering to maintain high-quality images and faces, face filtering to remove images that lack human faces, and keyword-based strategy to retain descriptions containing human-related terms (e.g., nationality, professions and names). Through these cleaning processes, FaceID-6M provides a high-quality dataset optimized for training powerful FaceID customization models, facilitating advancements in the field by offering an open resource for research and development. We conduct extensive experiments to show the effectiveness of our FaceID-6M, demonstrating that models trained on our FaceID-6M dataset achieve performance that is comparable to, and slightly better than currently available industrial models. Additionally, to support and advance research in the FaceID customization community, we make our code, datasets, and models fully publicly available. Our codes, models, and datasets are available at: https://github.com/ShuheSH/FaceID-6M.
Authors: Haiyang Xie, Xi Shen, Shihua Huang, Qirui Wang, Zheng Wang
Abstract: Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing. This enables improved detection accuracy and more efficient hardware designs by bypassing the ISP. However, RAW object detection is challenging due to limited training data, unbalanced pixel distributions, and sensor noise. To address this, we propose SimROD, a lightweight and effective approach for RAW object detection. We introduce a Global Gamma Enhancement (GGE) module, which applies a learnable global gamma transformation with only four parameters, improving feature representation while keeping the model efficient. Additionally, we leverage the green channel's richer signal to enhance local details, aligning with the human eye's sensitivity and Bayer filter design. Extensive experiments on multiple RAW object detection datasets and detectors demonstrate that SimROD outperforms state-of-the-art methods like RAW-Adapter and DIAP while maintaining efficiency. Our work highlights the potential of RAW data for real-world object detection. Code is available at https://ocean146.github.io/SimROD2025/.
Authors: Teng Xu, Taotao Zhou, Youjia Wang, Peng Yang, Simin Tang, Kuixiang Shao, Zifeng Tang, Yifei Liu, Xinyuan Chen, Hongshuang Wang, Xiaohui Wang, Huoqing Luo, Jingya Wang, Ji Hu, Jingyi Yu
Abstract: Analyzing animal behavior is crucial in advancing neuroscience, yet quantifying and deciphering its intricate dynamics remains a significant challenge. Traditional machine vision approaches, despite their ability to detect spontaneous behaviors, fall short due to limited interpretability and reliance on manual labeling, which restricts the exploration of the full behavioral spectrum. Here, we introduce MouseGPT, a Vision-Language Model (VLM) that integrates visual cues with natural language to revolutionize mouse behavior analysis. Built upon our first-of-its-kind dataset - incorporating pose dynamics and open-vocabulary behavioral annotations across over 42 million frames of diverse psychiatric conditions - MouseGPT provides a novel, context-rich method for comprehensive behavior interpretation. Our holistic analysis framework enables detailed behavior profiling, clustering, and novel behavior discovery, offering deep insights without the need for labor - intensive manual annotation. Evaluations reveal that MouseGPT surpasses existing models in precision, adaptability, and descriptive richness, positioning it as a transformative tool for ethology and for unraveling complex behavioral dynamics in animal models.
Authors: Zijing Hu, Fengda Zhang, Long Chen, Kun Kuang, Jiahui Li, Kaifeng Gao, Jun Xiao, Xin Wang, Wenwu Zhu
Abstract: Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue, reinforcement learning (RL) has been considered for diffusion model fine-tuning. Yet, RL's effectiveness is limited by the challenge of sparse reward, where feedback is only available at the end of the generation process. This makes it difficult to identify which actions during the denoising process contribute positively to the final generated image, potentially leading to ineffective or unnecessary denoising policies. To this end, this paper presents a novel RL-based framework that addresses the sparse reward problem when training diffusion models. Our framework, named $\text{B}^2\text{-DiffuRL}$, employs two strategies: \textbf{B}ackward progressive training and \textbf{B}ranch-based sampling. For one thing, backward progressive training focuses initially on the final timesteps of denoising process and gradually extends the training interval to earlier timesteps, easing the learning difficulty from sparse rewards. For another, we perform branch-based sampling for each training interval. By comparing the samples within the same branch, we can identify how much the policies of the current training interval contribute to the final image, which helps to learn effective policies instead of unnecessary ones. $\text{B}^2\text{-DiffuRL}$ is compatible with existing optimization algorithms. Extensive experiments demonstrate the effectiveness of $\text{B}^2\text{-DiffuRL}$ in improving prompt-image alignment and maintaining diversity in generated images. The code for this work is available.
Authors: Jaewoo Song, Daemin Park, Kanghyun Baek, Sangyub Lee, Jooyoung Choi, Eunji Kim, Sungroh Yoon
Abstract: Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose DefectFill, a novel method for realistic defect generation that requires only a few reference defect images. It leverages a fine-tuned inpainting diffusion model, optimized with our custom loss functions incorporating defect, object, and attention terms. It enables precise capture of detailed, localized defect features and their seamless integration into defect-free objects. Additionally, our Low-Fidelity Selection method further enhances the defect sample quality. Experiments show that DefectFill generates high-quality defect images, enabling visual inspection models to achieve state-of-the-art performance on the MVTec AD dataset.
Authors: Yi Xiao, Qiannan Han, Gang Shu, Guiping Liang, Hongyan Zhang, Song Wang, Zhihao Xu, Weican Wan, Chuang Li, Guitao Jiang, Wenbo Xiao
Abstract: Accurate body dimension and weight measurements are critical for optimizing poultry management, health assessment, and economic efficiency. This study introduces an innovative deep learning-based model leveraging multimodal data-2D RGB images from different views, depth images, and 3D point clouds-for the non-invasive estimation of duck body dimensions and weight. A dataset of 1,023 Linwu ducks, comprising over 5,000 samples with diverse postures and conditions, was collected to support model training. The proposed method innovatively employs PointNet++ to extract key feature points from point clouds, extracts and computes corresponding 3D geometric features, and fuses them with multi-view convolutional 2D features. A Transformer encoder is then utilized to capture long-range dependencies and refine feature interactions, thereby enhancing prediction robustness. The model achieved a mean absolute percentage error (MAPE) of 6.33% and an R2 of 0.953 across eight morphometric parameters, demonstrating strong predictive capability. Unlike conventional manual measurements, the proposed model enables high-precision estimation while eliminating the necessity for physical handling, thereby reducing animal stress and broadening its application scope. This study marks the first application of deep learning techniques to poultry body dimension and weight estimation, providing a valuable reference for the intelligent and precise management of the livestock industry with far-reaching practical significance.
Authors: Siyuan Yang, Shilin Lu, Shizheng Wang, Meng Hwa Er, Zengwei Zheng, Alex C. Kot
Abstract: This paper explores the promising interplay between spiking neural networks (SNNs) and event-based cameras for privacy-preserving human action recognition (HAR). The unique feature of event cameras in capturing only the outlines of motion, combined with SNNs' proficiency in processing spatiotemporal data through spikes, establishes a highly synergistic compatibility for event-based HAR. Previous studies, however, have been limited by SNNs' ability to process long-term temporal information, essential for precise HAR. In this paper, we introduce two novel frameworks to address this: temporal segment-based SNN (\textit{TS-SNN}) and 3D convolutional SNN (\textit{3D-SNN}). The \textit{TS-SNN} extracts long-term temporal information by dividing actions into shorter segments, while the \textit{3D-SNN} replaces 2D spatial elements with 3D components to facilitate the transmission of temporal information. To promote further research in event-based HAR, we create a dataset, \textit{FallingDetection-CeleX}, collected using the high-resolution CeleX-V event camera $(1280 \times 800)$, comprising 7 distinct actions. Extensive experimental results show that our proposed frameworks surpass state-of-the-art SNN methods on our newly collected dataset and three other neuromorphic datasets, showcasing their effectiveness in handling long-range temporal information for event-based HAR.
Authors: Yikun Ma, Yiqing Li, Jiawei Wu, Xing Luo, Zhi Jin
Abstract: Generative models have made remarkable advancements and are capable of producing high-quality content. However, performing controllable editing with generative models remains challenging, due to their inherent uncertainty in outputs. This challenge is praticularly pronounced in motion editing, which involves the processing of spatial information. While some physics-based generative methods have attempted to implement motion editing, they typically operate on single-view images with simple motions, such as translation and dragging. These methods struggle to handle complex rotation and stretching motions and ensure multi-view consistency, often necessitating resource-intensive retraining. To address these challenges, we propose MotionDiff, a training-free zero-shot diffusion method that leverages optical flow for complex multi-view motion editing. Specifically, given a static scene, users can interactively select objects of interest to add motion priors. The proposed Point Kinematic Model (PKM) then estimates corresponding multi-view optical flows during the Multi-view Flow Estimation Stage (MFES). Subsequently, these optical flows are utilized to generate multi-view motion results through decoupled motion representation in the Multi-view Motion Diffusion Stage (MMDS). Extensive experiments demonstrate that MotionDiff outperforms other physics-based generative motion editing methods in achieving high-quality multi-view consistent motion results. Notably, MotionDiff does not require retraining, enabling users to conveniently adapt it for various down-stream tasks.
Authors: Yishen Liu, Shengda Liu, Hudan Pan
Abstract: Medical report generation requires specialized expertise that general large models often fail to accurately capture. Moreover, the inherent repetition and similarity in medical data make it difficult for models to extract meaningful features, resulting in a tendency to overfit. So in this paper, we propose a multimodal model, Co-Attention Triple-LSTM Network (CA-TriNet), a deep learning model that combines transformer architectures with a Multi-LSTM network. Its Co-Attention module synergistically links a vision transformer with a text transformer to better differentiate medical images with similarities, augmented by an adaptive weight operator to catch and amplify image labels with minor similarities. Furthermore, its Triple-LSTM module refines generated sentences using targeted image objects. Extensive evaluations over three public datasets have demonstrated that CA-TriNet outperforms state-of-the-art models in terms of comprehensive ability, even pre-trained large language models on some metrics.
Authors: Ye Tian, Xin Xia, Yuxi Ren, Shanchuan Lin, Xing Wang, Xuefeng Xiao, Yunhai Tong, Ling Yang, Bin Cui
Abstract: Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic complexity of self-attention with respect to image or video resolution. While existing acceleration methods often compromise output quality or necessitate costly retraining, we observe that most diffusion models are pre-trained at lower resolutions, presenting an opportunity to exploit these low-resolution priors for more efficient inference without degrading performance. In this work, we introduce Bottleneck Sampling, a training-free framework that leverages low-resolution priors to reduce computational overhead while preserving output fidelity. Bottleneck Sampling follows a high-low-high denoising workflow: it performs high-resolution denoising in the initial and final stages while operating at lower resolutions in intermediate steps. To mitigate aliasing and blurring artifacts, we further refine the resolution transition points and adaptively shift the denoising timesteps at each stage. We evaluate Bottleneck Sampling on both image and video generation tasks, where extensive experiments demonstrate that it accelerates inference by up to 3$\times$ for image generation and 2.5$\times$ for video generation, all while maintaining output quality comparable to the standard full-resolution sampling process across multiple evaluation metrics.
Authors: Mingze Xu, Mingfei Gao, Shiyu Li, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan
Abstract: We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a streamlined training pipeline, and perform joint video-image training on a carefully curated data mixture of only publicly available datasets. Our primary focus is on highly efficient model scales (1B and 3B), demonstrating that even relatively small Video LLMs can achieve state-of-the-art performance on video understanding, meeting the demand for mobile-friendly models. Experimental results demonstrate that SF-LLaVA-1.5 achieves superior performance on a wide range of video and image tasks, with robust results at all model sizes (ranging from 1B to 7B). Notably, SF-LLaVA-1.5 achieves state-of-the-art results in long-form video understanding (e.g., LongVideoBench and MLVU) and excels at small scales across various video benchmarks.
Authors: Mehdi Moshtaghi, Siavash H. Khajavi, Joni Pajarinen
Abstract: We introduce RGB-Th-Bench, the first benchmark designed to evaluate the ability of Vision-Language Models (VLMs) to comprehend RGB-Thermal image pairs. While VLMs have demonstrated remarkable progress in visual reasoning and multimodal understanding, their evaluation has been predominantly limited to RGB-based benchmarks, leaving a critical gap in assessing their capabilities in infrared vision tasks. Existing visible-infrared datasets are either task-specific or lack high-quality annotations necessary for rigorous model evaluation. To address these limitations, RGB-Th-Bench provides a comprehensive evaluation framework covering 14 distinct skill dimensions, with a total of 1,600+ expert-annotated Yes/No questions. The benchmark employs two accuracy metrics: a standard question-level accuracy and a stricter skill-level accuracy, which evaluates model robustness across multiple questions within each skill dimension. This design ensures a thorough assessment of model performance, including resilience to adversarial and hallucinated responses. We conduct extensive evaluations on 19 state-of-the-art VLMs, revealing significant performance gaps in RGB-Thermal understanding. Our results show that even the strongest models struggle with thermal image comprehension, with performance heavily constrained by their RGB-based capabilities. Additionally, the lack of large-scale application-specific and expert-annotated thermal-caption-pair datasets in pre-training is an important reason of the observed performance gap. RGB-Th-Bench highlights the urgent need for further advancements in multimodal learning to bridge the gap between visible and thermal image understanding. The dataset is available through this link, and the evaluation code will also be made publicly available.
Authors: Chengjie Ge, Xueyang Fu, Peng He, Kunyu Wang, Chengzhi Cao, Zheng-Jun Zha
Abstract: Leveraging its robust linear global modeling capability, Mamba has notably excelled in computer vision. Despite its success, existing Mamba-based vision models have overlooked the nuances of event-driven tasks, especially in video reconstruction. Event-based video reconstruction (EBVR) demands spatial translation invariance and close attention to local event relationships in the spatio-temporal domain. Unfortunately, conventional Mamba algorithms apply static window partitions and standard reshape scanning methods, leading to significant losses in local connectivity. To overcome these limitations, we introduce EventMamba--a specialized model designed for EBVR tasks. EventMamba innovates by incorporating random window offset (RWO) in the spatial domain, moving away from the restrictive fixed partitioning. Additionally, it features a new consistent traversal serialization approach in the spatio-temporal domain, which maintains the proximity of adjacent events both spatially and temporally. These enhancements enable EventMamba to retain Mamba's robust modeling capabilities while significantly preserving the spatio-temporal locality of event data. Comprehensive testing on multiple datasets shows that EventMamba markedly enhances video reconstruction, drastically improving computation speed while delivering superior visual quality compared to Transformer-based methods.
Authors: Ahyun Seo, Minsu Cho
Abstract: Symmetry plays a vital role in understanding structural patterns, aiding object recognition and scene interpretation. This paper focuses on rotation symmetry, where objects remain unchanged when rotated around a central axis, requiring detection of rotation centers and supporting vertices. Traditional methods relied on hand-crafted feature matching, while recent segmentation models based on convolutional neural networks detect rotation centers but struggle with 3D geometric consistency due to viewpoint distortions. To overcome this, we propose a model that directly predicts rotation centers and vertices in 3D space and projects the results back to 2D while preserving structural integrity. By incorporating a vertex reconstruction stage enforcing 3D geometric priors -- such as equal side lengths and interior angles -- our model enhances robustness and accuracy. Experiments on the DENDI dataset show superior performance in rotation axis detection and validate the impact of 3D priors through ablation studies.
Authors: Jaeah Lee, Changwoon Choi, Young Min Kim, Jaesik Park
Abstract: Understanding 3D motion from videos presents inherent challenges due to the diverse types of movement, ranging from rigid and deformable objects to articulated structures. To overcome this, we propose Liv3Stroke, a novel approach for abstracting objects in motion with deformable 3D strokes. The detailed movements of an object may be represented by unstructured motion vectors or a set of motion primitives using a pre-defined articulation from a template model. Just as a free-hand sketch can intuitively visualize scenes or intentions with a sparse set of lines, we utilize a set of parametric 3D curves to capture a set of spatially smooth motion elements for general objects with unknown structures. We first extract noisy, 3D point cloud motion guidance from video frames using semantic features, and our approach deforms a set of curves to abstract essential motion features as a set of explicit 3D representations. Such abstraction enables an understanding of prominent components of motions while maintaining robustness to environmental factors. Our approach allows direct analysis of 3D object movements from video, tackling the uncertainty that typically occurs when translating real-world motion into recorded footage. The project page is accessible via: https://jaeah.me/liv3stroke_web
Authors: Weiyi You, Mingyang Zhang, Leheng Zhang, Xingyu Zhou, Kexuan Shi, Shuhang Gu
Abstract: Current diffusion-based super-resolution (SR) approaches achieve commendable performance at the cost of high inference overhead. Therefore, distillation techniques are utilized to accelerate the multi-step teacher model into one-step student model. Nevertheless, these methods significantly raise training costs and constrain the performance of the student model by the teacher model. To overcome these tough challenges, we propose Consistency Trajectory Matching for Super-Resolution (CTMSR), a distillation-free strategy that is able to generate photo-realistic SR results in one step. Concretely, we first formulate a Probability Flow Ordinary Differential Equation (PF-ODE) trajectory to establish a deterministic mapping from low-resolution (LR) images with noise to high-resolution (HR) images. Then we apply the Consistency Training (CT) strategy to directly learn the mapping in one step, eliminating the necessity of pre-trained diffusion model. To further enhance the performance and better leverage the ground-truth during the training process, we aim to align the distribution of SR results more closely with that of the natural images. To this end, we propose to minimize the discrepancy between their respective PF-ODE trajectories from the LR image distribution by our meticulously designed Distribution Trajectory Matching (DTM) loss, resulting in improved realism of our recovered HR images. Comprehensive experimental results demonstrate that the proposed methods can attain comparable or even superior capabilities on both synthetic and real datasets while maintaining minimal inference latency.
Authors: Jinnan Chen, Lingting Zhu, Zeyu Hu, Shengju Qian, Yugang Chen, Xin Wang, Gim Hee Lee
Abstract: Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D generation presents three key challenges: the unordered nature of 3D data conflicts with sequential next-token prediction paradigm, conventional vector quantization approaches incur substantial compression loss when applied to 3D meshes, and the lack of efficient scaling strategies for higher resolution latent prediction. To address these challenges, we introduce MAR-3D, which integrates a pyramid variational autoencoder with a cascaded masked auto-regressive transformer (Cascaded MAR) for progressive latent upscaling in the continuous space. Our architecture employs random masking during training and auto-regressive denoising in random order during inference, naturally accommodating the unordered property of 3D latent tokens. Additionally, we propose a cascaded training strategy with condition augmentation that enables efficiently up-scale the latent token resolution with fast convergence. Extensive experiments demonstrate that MAR-3D not only achieves superior performance and generalization capabilities compared to existing methods but also exhibits enhanced scaling capabilities compared to joint distribution modeling approaches (e.g., diffusion transformers).
Authors: Theo Di Piazza, Carole Lazarus, Olivier Nempont, Loic Boussel
Abstract: The rapid increase in the number of Computed Tomography (CT) scan examinations has created an urgent need for automated tools, such as organ segmentation, anomaly classification, and report generation, to assist radiologists with their growing workload. Multi-label classification of Three-Dimensional (3D) CT scans is a challenging task due to the volumetric nature of the data and the variety of anomalies to be detected. Existing deep learning methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies effectively, while Vision Transformers require extensive pre-training, posing challenges for practical use. Additionally, these existing methods do not explicitly model the radiologist's navigational behavior while scrolling through CT scan slices, which requires both global context understanding and local detail awareness. In this study, we present CT-Scroll, a novel global-local attention model specifically designed to emulate the scrolling behavior of radiologists during the analysis of 3D CT scans. Our approach is evaluated on two public datasets, demonstrating its efficacy through comprehensive experiments and an ablation study that highlights the contribution of each model component.
Authors: Yinan Sun, Xiongkuo Min, Zicheng Zhang, Yixuan Gao, Yuqin Cao, Guangtao Zhai
Abstract: The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models are prone to hallucinations, which limit their reliability as artificial intelligence systems. While this issue is extensively researched in natural language processing and image captioning, there remains a lack of investigation of hallucinations in Low-level Visual Perception and Understanding (HLPU), especially in the context of image quality assessment tasks. We consider that these hallucinations arise from an absence of clear self-awareness within the models. To address this issue, we first introduce the HLPU instruction database, the first instruction database specifically focused on hallucinations in low-level vision tasks. This database contains approximately 200K question-answer pairs and comprises four subsets, each covering different types of instructions. Subsequently, we propose the Self-Awareness Failure Elimination (SAFEQA) model, which utilizes image features, salient region features and quality features to improve the perception and comprehension abilities of the model in low-level vision tasks. Furthermore, we propose the Enhancing Self-Awareness Preference Optimization (ESA-PO) framework to increase the model's awareness of knowledge boundaries, thereby mitigating the incidence of hallucination. Finally, we conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations. Notably, our proposed method improves both accuracy and self-awareness of the proposed model and outperforms close-source models in terms of various evaluation metrics.
Authors: Yuhao Huang, Ao Chang, Haoran Dou, Xing Tao, Xinrui Zhou, Yan Cao, Ruobing Huang, Alejandro F Frangi, Lingyun Bao, Xin Yang, Dong Ni
Abstract: Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: (1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. (2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents' erasing process precisely, thereby avoiding both under- and over-segmentation. (3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms.
Authors: Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Minglan Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Abstract: Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods improve VLM reasoning via Chain-of-Thought (CoT) supervised fine-tuning, using meticulously annotated training data to enhance visual reasoning capabilities. However, this training paradigm may lead to overfitting and cognitive rigidity, restricting the model's ability to transfer visual reasoning skills across domains and limiting its real-world applicability. To address these limitations, we propose Reason-RFT, a novel reinforcement fine-tuning framework that significantly enhances generalization capabilities in visual reasoning tasks. Reason-RFT introduces a two-phase training framework for visual reasoning: (1) Supervised Fine-Tuning (SFT) with curated Chain-of-Thought (CoT) data activates the reasoning potential of Vision-Language Models (VLMs), followed by (2) Group Relative Policy Optimization (GRPO)-based reinforcement learning that generates multiple reasoning-response pairs, significantly enhancing generalization in visual reasoning tasks. To evaluate Reason-RFT's visual reasoning capabilities, we reconstructed a comprehensive dataset spanning visual counting, structure perception, and spatial transformation. Experimental results demonstrate Reasoning-RFT's three key advantages: (1) Performance Enhancement: achieving state-of-the-art results across multiple tasks, outperforming most mainstream open-source and proprietary models; (2) Generalization Superiority: consistently maintaining robust performance across diverse tasks and domains, outperforming alternative training paradigms; (3) Data Efficiency: excelling in few-shot learning scenarios while surpassing full-dataset SFT baselines. Project website: https://tanhuajie.github.io/ReasonRFT
Authors: Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi
Abstract: Multimodal disinformation, from 'deepfakes' to simple edits that deceive, is an important societal problem. Yet at the same time, the vast majority of media edits are harmless -- such as a filtered vacation photo. The difference between this example, and harmful edits that spread disinformation, is one of intent. Recognizing and describing this intent is a major challenge for today's AI systems. We present the task of Edited Media Understanding, requiring models to answer open-ended questions that capture the intent and implications of an image edit. We introduce a dataset for our task, EMU, with 48k question-answer pairs written in rich natural language. We evaluate a wide variety of vision-and-language models for our task, and introduce a new model PELICAN, which builds upon recent progress in pretrained multimodal representations. Our model obtains promising results on our dataset, with humans rating its answers as accurate 40.35% of the time. At the same time, there is still much work to be done -- humans prefer human-annotated captions 93.56% of the time -- and we provide analysis that highlights areas for further progress.
Authors: Huiyi Wang, Haodong Lu, Lina Yao, Dong Gong
Abstract: Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation on downstream tasks by adding learnable adapters or prompts upon the frozen PTMs. However, many existing PTM-based CL methods use restricted adaptation on a fixed set of these modules to avoid forgetting, suffering from limited CL ability. Periodically adding task-specific modules results in linear model growth rate and impaired knowledge reuse. We propose Self-Expansion of pre-trained models with Modularized Adaptation (SEMA), a novel approach to enhance the control of stability-plasticity balance in PTM-based CL. SEMA automatically decides to reuse or add adapter modules on demand in CL, depending on whether significant distribution shift that cannot be handled is detected at different representation levels. We design modular adapter consisting of a functional adapter and a representation descriptor. The representation descriptors are trained as a distribution shift indicator and used to trigger self-expansion signals. For better composing the adapters, an expandable weighting router is learned jointly for mixture of adapter outputs. SEMA enables better knowledge reuse and sub-linear expansion rate. Extensive experiments demonstrate the effectiveness of the proposed self-expansion method, achieving state-of-the-art performance compared to PTM-based CL methods without memory rehearsal. Code is available at https://github.com/huiyiwang01/SEMA-CL.
Authors: Pooya Ashtari, Pourya Behmandpoor, Fateme Nateghi Haredasht, Jonathan H. Chen, Panagiotis Patrinos, Sabine Van Huffel
Abstract: Lossy image compression is essential for efficient transmission and storage. Traditional compression methods mainly rely on discrete cosine transform (DCT) or singular value decomposition (SVD), both of which represent image data in continuous domains and, therefore, necessitate carefully designed quantizers. Notably, these methods consider quantization as a separate step, where quantization errors cannot be incorporated into the compression process. The sensitivity of these methods, especially SVD-based ones, to quantization errors significantly degrades reconstruction quality. To address this issue, we introduce a quantization-aware matrix factorization (QMF) to develop a novel lossy image compression method. QMF provides a low-rank representation of the image data as a product of two smaller factor matrices, with elements constrained to bounded integer values, thereby effectively integrating quantization with low-rank approximation. We propose an efficient, provably convergent iterative algorithm for QMF using a block coordinate descent (BCD) scheme, with subproblems having closed-form solutions. Our experiments on the Kodak and CLIC 2024 datasets demonstrate that our QMF compression method consistently outperforms JPEG at low bit rates below 0.25 bits per pixel (bpp) and remains comparable at higher bit rates. We also assessed our method's capability to preserve visual semantics by evaluating an ImageNet pre-trained classifier on compressed images. Remarkably, our method improved top-1 accuracy by over 5 percentage points compared to JPEG at bit rates under 0.25 bpp. The project is available at https://github.com/pashtari/lrf .
Authors: Xing Chen, Dongshu Liu, Jeremie Laydevant, Julie Grollier
Abstract: Agents that operate autonomously benefit from lifelong learning capabilities. However, compatible training algorithms must comply with the decentralized nature of these systems, which imposes constraints on both the parameter counts and the computational resources. The Forward-Forward (FF) algorithm is one of these. FF relies only on feedforward operations, the same used for inference, for optimizing layer-wise objectives. This purely forward approach eliminates the need for transpose operations required in traditional backpropagation. Despite its potential, FF has failed to reach state-of-the-art performance on most standard benchmark tasks, in part due to unreliable negative data generation methods for unsupervised learning. In this work, we propose the Self-Contrastive Forward-Forward (SCFF) algorithm, a competitive training method aimed at closing this performance gap. Inspired by standard self-supervised contrastive learning for vision tasks, SCFF generates positive and negative inputs applicable across various datasets. The method demonstrates superior performance compared to existing unsupervised local learning algorithms on several benchmark datasets, including MNIST, CIFAR-10, STL-10, and Tiny ImageNet. We extend FF's application to training recurrent neural networks, expanding its utility to sequential data tasks. These findings pave the way for high-accuracy, real-time learning on resource-constrained edge devices.
Authors: Yizhi Li, Ge Zhang, Yinghao Ma, Ruibin Yuan, Kang Zhu, Hangyu Guo, Yiming Liang, Jiaheng Liu, Zekun Wang, Jian Yang, Siwei Wu, Xingwei Qu, Jinjie Shi, Xinyue Zhang, Zhenzhu Yang, Xiangzhou Wang, Zhaoxiang Zhang, Zachary Liu, Emmanouil Benetos, Wenhao Huang, Chenghua Lin
Abstract: Recent advancements in multimodal large language models (MLLMs) have focused on integrating multiple modalities, yet their ability to simultaneously process and reason across different inputs remains underexplored. We introduce OmniBench, a novel benchmark designed to evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. We define language models capable of such tri-modal processing as omni-language models (OLMs). OmniBench features high-quality human annotations that require integrated understanding across all modalities. Our evaluation reveals that: i) open-source OLMs show significant limitations in instruction-following and reasoning in tri-modal contexts; and ii) most baseline models perform poorly (around 50% accuracy) even with textual alternatives to image/audio inputs. To address these limitations, we develop OmniInstruct, an 96K-sample instruction tuning dataset for training OLMs. We advocate for developing more robust tri-modal integration techniques and training strategies to enhance OLM performance. Codes and data could be found at our repo (https://github.com/multimodal-art-projection/OmniBench).
URLs: https://github.com/multimodal-art-projection/OmniBench).
Authors: Luca Zhou, Daniele Solombrino, Donato Crisostomi, Maria Sofia Bucarelli, Fabrizio Silvestri, Emanuele Rodol\`a
Abstract: Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic stands out for its simplicity and effectiveness. In this paper, we motivate the effectiveness of task vectors by linking them to multi-task gradients. We show that in a single-epoch scenario, if the optimization is performed via gradient descent, task vectors are after one step mathematically equivalent to the gradients obtained via gradient descent in a multi-task setting, and still approximate these gradients in subsequent epochs. Furthermore, we show that the effectiveness of task vectors is largely driven by the first epoch's gradient. Given this parallel between task vectors and gradients, we propose viewing model merging as a single step in an iterative process that alternates between tuning and merging (ATM). We then propose two ways to utilize ATM. The first is to replace multi-task learning with ATM in scenarios where data sharing is prohibited, such as federated learning. The second is to improve the outcome of any model merging algorithm by applying a few post-hoc iterations of ATM on a small validation dataset, which is commonly available for hyperparameter tuning. Finally, we provide both empirical and theoretical support for the effectiveness of ATM, demonstrating that it minimizes an upper bound on the loss obtained by jointly finetuning all tasks.
Authors: Shaokai Wu, Yuxiang Lu, Wei Ji, Suizhi Huang, Fengyu Yang, Shalayiding Sirejiding, Qichen He, Jing Tong, Yanbiao Ji, Yue Ding, Hongtao Lu
Abstract: Computed Tomography (CT) is a widely used imaging technique that provides detailed cross-sectional views of objects. Over the past decade, Deep Learning-based Reconstruction (DLR) methods have led efforts to enhance image quality and reduce noise, yet they often require large amounts of data and are computationally intensive. Inspired by recent advancements in scene reconstruction, some approaches have adapted NeRF and 3D Gaussian Splatting (3DGS) techniques for CT reconstruction. However, these methods are not ideal for direct 3D volume reconstruction. In this paper, we propose a novel Discretized Gaussian Representation (DGR) for CT reconstruction, which directly reconstructs the 3D volume using a set of discretized Gaussian functions in an end-to-end manner. To further enhance computational efficiency, we introduce a Fast Volume Reconstruction technique that aggregates the contributions of these Gaussians into a discretized volume in a highly parallelized fashion. Our extensive experiments on both real-world and synthetic datasets demonstrate that DGR achieves superior reconstruction quality and significantly improved computational efficiency compared to existing DLR and instance reconstruction methods. Our code has been provided for review purposes and will be made publicly available upon publication.
Authors: Zhi Zhang, Srishti Yadav, Fengze Han, Ekaterina Shutova
Abstract: The recent advancements in auto-regressive multimodal large language models (MLLMs) have demonstrated promising progress for vision-language tasks. While there exists a variety of studies investigating the processing of linguistic information within large language models, little is currently known about the inner working mechanism of MLLMs and how linguistic and visual information interact within these models. In this study, we aim to fill this gap by examining the information flow between different modalities -- language and vision -- in MLLMs, focusing on visual question answering. Specifically, given an image-question pair as input, we investigate where in the model and how the visual and linguistic information are combined to generate the final prediction. Conducting experiments with a series of models from the LLaVA series, we find that there are two distinct stages in the process of integration of the two modalities. In the lower layers, the model first transfers the more general visual features of the whole image into the representations of (linguistic) question tokens. In the middle layers, it once again transfers visual information about specific objects relevant to the question to the respective token positions of the question. Finally, in the higher layers, the resulting multimodal representation is propagated to the last position of the input sequence for the final prediction. Overall, our findings provide a new and comprehensive perspective on the spatial and functional aspects of image and language processing in the MLLMs, thereby facilitating future research into multimodal information localization and editing. Our code and collected dataset are released here: https://github.com/FightingFighting/cross-modal-information-flow-in-MLLM.git.
URLs: https://github.com/FightingFighting/cross-modal-information-flow-in-MLLM.git.
Authors: Muchao Ye, Weiyang Liu, Pan He
Abstract: The rapid advancement of vision-language models (VLMs) has established a new paradigm in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and provide comprehendible explanations for the decisions. Existing work in this direction often assumes the complex reasoning required for VAD exceeds the capabilities of pretrained VLMs. Consequently, these approaches either incorporate specialized reasoning modules during inference or rely on instruction tuning datasets through additional training to adapt VLMs for VAD. However, such strategies often incur substantial computational costs or data annotation overhead. To address these challenges in explainable VAD, we introduce a verbalized learning framework named VERA that enables VLMs to perform VAD without model parameter modifications. Specifically, VERA automatically decomposes the complex reasoning required for VAD into reflections on simpler, more focused guiding questions capturing distinct abnormal patterns. It treats these reflective questions as learnable parameters and optimizes them through data-driven verbal interactions between learner and optimizer VLMs, using coarsely labeled training data. During inference, VERA embeds the learned questions into model prompts to guide VLMs in generating segment-level anomaly scores, which are then refined into frame-level scores via the fusion of scene and temporal contexts. Experimental results on challenging benchmarks demonstrate that the learned questions of VERA are highly adaptable, significantly improving both detection performance and explainability of VLMs for VAD.
Authors: Pingping Tao, Haixia Liu, Jing Su, Xiaochen Yang, Hongchen Tan
Abstract: Diffusion models have indeed shown great promise in solving inverse problems in image processing. In this paper, we propose a novel, problem-agnostic diffusion model called the maximum a posteriori (MAP)-based guided term estimation method for inverse problems. To leverage unconditionally pretrained diffusion models to address conditional generation tasks, we divide the conditional score function into two terms according to Bayes' rule: an unconditional score function (approximated by a pretrained score network) and a guided term, which is estimated using a novel MAP-based method that incorporates a Gaussian-type prior of natural images. This innovation allows us to better capture the intrinsic properties of the data, leading to improved performance. Numerical results demonstrate that our method preserves contents more effectively compared to state-of-the-art methods--for example, maintaining the structure of glasses in super-resolution tasks and producing more coherent results in the neighborhood of masked regions during inpainting.
Authors: Malitha Gunawardhana, Fangqiang Xu, Jichao Zhao
Abstract: Atrial fibrillation (AF) is the most common cardiac arrhythmia, significantly contributing to mortality, particularly in older populations. While pulmonary vein isolation is a standard treatment, its effectiveness is limited in patients with persistent AF. Recent research highlights the importance of targeting additional atrial regions, particularly fibrotic areas identified via late gadolinium-enhanced MRI (LGE-MRI). However, existing manual segmentation methods are time-consuming and prone to variability. Deep learning techniques, particularly convolutional neural networks (CNNs), have shown promise in automating segmentation. However, most studies focus solely on the left atrium (LA) and rely on small datasets, limiting generalizability. In this paper, we propose a novel two-stage framework incorporating ResNeXt encoders and a cyclic learning rate to segment both the right atrium (RA) and LA walls and cavities in LGE-MRIs. Our method aims to improve the segmentation of challenging small structures, such as atrial walls while maintaining high performance in larger regions like the atrial cavities. The results demonstrate that our approach offers superior segmentation accuracy and robustness compared to traditional architectures, particularly for imbalanced class structures.
Authors: Cesare Maria Dalbagno, Manuel de Castro Ribeiro Jardim, Mihnea Anghelu\c{t}\u{a}
Abstract: The goal of this study is to investigate whether latent space representations of visual stimuli and fMRI data share common information. Decoding and reconstructing stimuli from fMRI data remains a challenge in AI and neuroscience, with significant implications for understanding neural representations and improving the interpretability of Artificial Neural Networks (ANNs). In this preliminary study, we investigate the feasibility of such reconstruction by examining the similarity between the latent spaces of one autoencoder (AE) and one vision transformer (ViT) trained on fMRI and image data, respectively. Using representational similarity analysis (RSA), we found that the latent spaces of the two domains appear different. However, these initial findings are inconclusive, and further research is needed to explore this relationship more thoroughly.
Authors: Lee Chae-Yeon, Oh Hyun-Bin, Han EunGi, Kim Sung-Bin, Suekyeong Nam, Tae-Hyun Oh
Abstract: Recent advancements in speech-driven 3D talking head generation have made significant progress in lip synchronization. However, existing models still struggle to capture the perceptual alignment between varying speech characteristics and corresponding lip movements. In this work, we claim that three criteria -- Temporal Synchronization, Lip Readability, and Expressiveness -- are crucial for achieving perceptually accurate lip movements. Motivated by our hypothesis that a desirable representation space exists to meet these three criteria, we introduce a speech-mesh synchronized representation that captures intricate correspondences between speech signals and 3D face meshes. We found that our learned representation exhibits desirable characteristics, and we plug it into existing models as a perceptual loss to better align lip movements to the given speech. In addition, we utilize this representation as a perceptual metric and introduce two other physically grounded lip synchronization metrics to assess how well the generated 3D talking heads align with these three criteria. Experiments show that training 3D talking head generation models with our perceptual loss significantly improve all three aspects of perceptually accurate lip synchronization. Codes and datasets are available at https://perceptual-3d-talking-head.github.io/.
Authors: Giovanni Compiani, Ilya Morozov, Stephan Seiler
Abstract: We propose a demand estimation method that leverages unstructured text and image data to infer substitution patterns. Using pre-trained deep learning models, we extract embeddings from product images and textual descriptions and incorporate them into a random coefficients logit model. This approach enables researchers to estimate demand even when they lack data on product attributes or when consumers value hard-to-quantify attributes, such as visual design or functional benefits. Using data from a choice experiment, we show that our approach outperforms standard attribute-based models in counterfactual predictions of consumers' second choices. We also apply it across 40 product categories on Amazon and consistently find that text and image data help identify close substitutes within each category.