Authors: Nicholas Merchant, Haitz S\'aez de Oc\'ariz Borde, Andrei Cristian Popescu, Carlos Garcia Jurado Suarez
Abstract: We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable outputs. In this work, we propose that enforcing a consistent caption structure during training can significantly improve model controllability and alignment. We introduce Re-LAION-Caption 19M, a high-quality subset of Re-LAION-5B, comprising 19 million 1024x1024 images with captions generated by a Mistral 7B Instruct-based LLaVA-Next model. Each caption follows a four-part template: subject, setting, aesthetics, and camera details. We fine-tune PixArt-$\Sigma$ and Stable Diffusion 2 using both structured and randomly shuffled captions, and show that structured versions consistently yield higher text-image alignment scores using visual question answering (VQA) models. The dataset is publicly available at https://huggingface.co/datasets/supermodelresearch/Re-LAION-Caption19M.
URLs: https://huggingface.co/datasets/supermodelresearch/Re-LAION-Caption19M.
Authors: Binjia Zhou, Hengrui Lou, Lizhe Chen, Haoyuan Li, Dawei Luo, Shuai Chen, Jie Lei, Zunlei Feng, Yijun Bei
Abstract: With the swift progression of image generation technology, the widespread emergence of facial deepfakes poses significant challenges to the field of security, thus amplifying the urgent need for effective deepfake detection.Existing techniques for face forgery detection can broadly be categorized into two primary groups: visual-based methods and multimodal approaches. The former often lacks clear explanations for forgery details, while the latter, which merges visual and linguistic modalities, is more prone to the issue of hallucinations.To address these shortcomings, we introduce a visual detail enhanced self-correction framework, designated CorrDetail, for interpretable face forgery detection. CorrDetail is meticulously designed to rectify authentic forgery details when provided with error-guided questioning, with the aim of fostering the ability to uncover forgery details rather than yielding hallucinated responses. Additionally, to bolster the reliability of its findings, a visual fine-grained detail enhancement module is incorporated, supplying CorrDetail with more precise visual forgery details. Ultimately, a fusion decision strategy is devised to further augment the model's discriminative capacity in handling extreme samples, through the integration of visual information compensation and model bias reduction.Experimental results demonstrate that CorrDetail not only achieves state-of-the-art performance compared to the latest methodologies but also excels in accurately identifying forged details, all while exhibiting robust generalization capabilities.
Authors: Aquino Joctum, John Kandiri
Abstract: Autonomous vehicle perception systems require robust pedestrian detection, particularly on geometrically complex roadways like Type-S curved surfaces, where standard RGB camera-based methods face limitations. This paper introduces YOLO-APD, a novel deep learning architecture enhancing the YOLOv8 framework specifically for this challenge. YOLO-APD integrates several key architectural modifications: a parameter-free SimAM attention mechanism, computationally efficient C3Ghost modules, a novel SimSPPF module for enhanced multi-scale feature pooling, the Mish activation function for improved optimization, and an Intelligent Gather & Distribute (IGD) module for superior feature fusion in the network's neck. The concept of leveraging vehicle steering dynamics for adaptive region-of-interest processing is also presented. Comprehensive evaluations on a custom CARLA dataset simulating complex scenarios demonstrate that YOLO-APD achieves state-of-the-art detection accuracy, reaching 77.7% mAP@0.5:0.95 and exceptional pedestrian recall exceeding 96%, significantly outperforming baseline models, including YOLOv8. Furthermore, it maintains real-time processing capabilities at 100 FPS, showcasing a superior balance between accuracy and efficiency. Ablation studies validate the synergistic contribution of each integrated component. Evaluation on the KITTI dataset confirms the architecture's potential while highlighting the need for domain adaptation. This research advances the development of highly accurate, efficient, and adaptable perception systems based on cost-effective sensors, contributing to enhanced safety and reliability for autonomous navigation in challenging, less-structured driving environments.
Authors: Alexandr A. Kalinin, Paula Llanos, Theresa Maria Sommer, Giovanni Sestini, Xinhai Hou, Jonathan Z. Sexton, Xiang Wan, Ivo D. Dinov, Brian D. Athey, Nicolas Rivron, Anne E. Carpenter, Beth Cimini, Shantanu Singh, Matthew J. O'Meara
Abstract: Microscopy enables direct observation of cellular morphology in 3D, with transmitted-light methods offering low-cost, minimally invasive imaging and fluorescence microscopy providing specificity and contrast. Virtual staining combines these strengths by using machine learning to predict fluorescence images from label-free inputs. However, training of existing methods typically relies on loss functions that treat all pixels equally, thus reproducing background noise and artifacts instead of focusing on biologically meaningful signals. We introduce Spotlight, a simple yet powerful virtual staining approach that guides the model to focus on relevant cellular structures. Spotlight uses histogram-based foreground estimation to mask pixel-wise loss and to calculate a Dice loss on soft-thresholded predictions for shape-aware learning. Applied to a 3D benchmark dataset, Spotlight improves morphological representation while preserving pixel-level accuracy, resulting in virtual stains better suited for downstream tasks such as segmentation and profiling.
Authors: Vishal Nedungadi, Xingguo Xiong, Aike Potze, Ron Van Bree, Tao Lin, Marc Ru{\ss}wurm, Ioannis N. Athanasiadis
Abstract: Food security remains a global concern as population grows and climate change intensifies, demanding innovative solutions for sustainable agricultural productivity. Recent advances in foundation models have demonstrated remarkable performance in remote sensing and climate sciences, and therefore offer new opportunities for agricultural monitoring. However, their application in challenges related to agriculture-such as crop type mapping, crop phenology estimation, and crop yield estimation-remains under-explored. In this work, we quantitatively evaluate existing foundational models to assess their effectivity for a representative set of agricultural tasks. From an agricultural domain perspective, we describe a requirements framework for an ideal agricultural foundation model (CropFM). We then survey and compare existing general-purpose foundational models in this framework and empirically evaluate two exemplary of them in three representative agriculture specific tasks. Finally, we highlight the need for a dedicated foundational model tailored specifically to agriculture.
Authors: Jose M. Montero, Jose-Luis Lisani
Abstract: Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving underwater image quality by integrating human subjective assessments into the training process. To this end, we utilize publicly available datasets containing underwater images labeled by experts as either high or low quality. Our method involves first training a classifier network to distinguish between high- and low-quality images. Subsequently, generative adversarial networks (GANs) are trained using various enhancement criteria to refine the low-quality images. The performance of the GAN models is evaluated using quantitative metrics such as PSNR, SSIM, and UIQM, as well as through qualitative analysis. Results demonstrate that the proposed model -- particularly when incorporating criteria such as color fidelity and image sharpness -- achieves substantial improvements in both perceived and measured image quality.
Authors: Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani
Abstract: Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous data remains a challenge. While prompt tuning has emerged as a popular parameter-efficient approach in personalized federated learning, existing methods often sacrifice generalization in favor of personalization, struggling particularly on unseen classes or domains. In this work, we propose pFedMMA, the first personalized federated learning framework that leverages multi-modal adapters for vision-language tasks. Each adapter contains modality-specific up- and down-projection layers alongside a globally shared projection that aligns cross-modal features. Our asymmetric optimization strategy allows clients to locally adapt to personalized data distributions while collaboratively training the shared projection to improve global generalization. This design is also communication-efficient, as only the shared component is exchanged during rounds. Through extensive experiments across eleven datasets, including domain- and label-shift scenarios, we show that pFedMMA achieves state-of-the-art trade-offs between personalization and generalization, outperforming recent federated prompt tuning methods. The code is available at https://github.com/sajjad-ucsb/pFedMMA.
Authors: Pengfei Zhou, Jie Xia, Xiaopeng Peng, Wangbo Zhao, Zilong Ye, Zekai Li, Suorong Yang, Jiadong Pan, Yuanxiang Chen, Ziqiao Wang, Kai Wang, Qian Zheng, Xiaojun Chang, Gang Pan, Shurong Dong, Kaipeng Zhang, Yang You
Abstract: Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveraging recent advances in brain-computer interfaces (BCIs) and generative models, we propose LoongX, a hands-free image editing approach driven by multimodal neurophysiological signals. LoongX utilizes state-of-the-art diffusion models trained on a comprehensive dataset of 23,928 image editing pairs, each paired with synchronized electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), photoplethysmography (PPG), and head motion signals that capture user intent. To effectively address the heterogeneity of these signals, LoongX integrates two key modules. The cross-scale state space (CS3) module encodes informative modality-specific features. The dynamic gated fusion (DGF) module further aggregates these features into a unified latent space, which is then aligned with edit semantics via fine-tuning on a diffusion transformer (DiT). Additionally, we pre-train the encoders using contrastive learning to align cognitive states with semantic intentions from embedded natural language. Extensive experiments demonstrate that LoongX achieves performance comparable to text-driven methods (CLIP-I: 0.6605 vs. 0.6558; DINO: 0.4812 vs. 0.4636) and outperforms them when neural signals are combined with speech (CLIP-T: 0.2588 vs. 0.2549). These results highlight the promise of neural-driven generative models in enabling accessible, intuitive image editing and open new directions for cognitive-driven creative technologies. Datasets and code will be released to support future work and foster progress in this emerging area.
Authors: Aliasghar Khani, Arianna Rampini, Bruno Roy, Larasika Nadela, Noa Kaplan, Evan Atherton, Derek Cheung, Jacky Bibliowicz
Abstract: Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual agents to human-robot interaction. As the field has rapidly progressed with the introduction of diverse modeling paradigms including GANs, autoencoders, autoregressive models, and diffusion-based techniques, each approach brings its own advantages and limitations. This growing diversity has created a need for a comprehensive and structured review that specifically examines recent developments from the perspective of the generative approach employed. In this survey, we provide an in-depth categorization of motion generation methods based on their underlying generative strategies. Our main focus is on papers published in top-tier venues since 2023, reflecting the most recent advancements in the field. In addition, we analyze architectural principles, conditioning mechanisms, and generation settings, and compile a detailed overview of the evaluation metrics and datasets used across the literature. Our objective is to enable clearer comparisons and identify open challenges, thereby offering a timely and foundational reference for researchers and practitioners navigating the rapidly evolving landscape of motion generation.
Authors: Lanqing Guo, Yufei Wang, Hezhen Hu, Yan Zheng, Yeying Jin, Siyu Huang, Zhangyang Wang
Abstract: Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussian Splatting (3DGS), where scenes are represented by a series of Gaussians, this structure allows for precise regional edits, offering enhanced control over specific areas of the scene; however, the challenge lies in the fact that 3D semantic parsing often underperforms compared to its 2D counterpart, making targeted manipulations within 3D spaces more difficult and limiting the fidelity of edits, which we address by leveraging 2D diffusion editing to accurately identify modification regions in each view, followed by inverse rendering for 3D localization, then refining the frontal view and initializing a coarse 3DGS with consistent views and approximate shapes derived from depth maps predicted by a 2D foundation model, thereby supporting an iterative, view-consistent editing process that gradually enhances structural details and textures to ensure coherence across perspectives. Experiments demonstrate that our method achieves state-of-the-art performance while delivering up to a $4\times$ speedup, providing a more efficient and effective approach to 3D scene local editing.
Authors: Shiting Xiao, Rishabh Kabra, Yuhang Li, Donghyun Lee, Joao Carreira, Priyadarshini Panda
Abstract: The ability to segment objects based on open-ended language prompts remains a critical challenge, requiring models to ground textual semantics into precise spatial masks while handling diverse and unseen categories. We present OpenWorldSAM, a framework that extends the prompt-driven Segment Anything Model v2 (SAM2) to open-vocabulary scenarios by integrating multi-modal embeddings extracted from a lightweight vision-language model (VLM). Our approach is guided by four key principles: i) Unified prompting: OpenWorldSAM supports a diverse range of prompts, including category-level and sentence-level language descriptions, providing a flexible interface for various segmentation tasks. ii) Efficiency: By freezing the pre-trained components of SAM2 and the VLM, we train only 4.5 million parameters on the COCO-stuff dataset, achieving remarkable resource efficiency. iii) Instance Awareness: We enhance the model's spatial understanding through novel positional tie-breaker embeddings and cross-attention layers, enabling effective segmentation of multiple instances. iv) Generalization: OpenWorldSAM exhibits strong zero-shot capabilities, generalizing well on unseen categories and an open vocabulary of concepts without additional training. Extensive experiments demonstrate that OpenWorldSAM achieves state-of-the-art performance in open-vocabulary semantic, instance, and panoptic segmentation across multiple benchmarks, including ADE20k, PASCAL, ScanNet, and SUN-RGBD.
Authors: Inayat Rasool, Pappu Kumar Yadav, Amee Parmar, Hasan Mirzakhaninafchi, Rikesh Budhathoki, Zain Ul Abideen Usmani, Supriya Paudel, Ivan Perez Olivera, Eric Jone
Abstract: Uniform and excessive herbicide application in modern agriculture contributes to increased input costs, environmental pollution, and the emergence of herbicide resistant weeds. To address these challenges, we developed a vision guided, AI-driven variable rate sprayer system capable of detecting weed presence, estimating canopy size, and dynamically adjusting nozzle activation in real time. The system integrates lightweight YOLO11n and YOLO11n-seg deep learning models, deployed on an NVIDIA Jetson Orin Nano for onboard inference, and uses an Arduino Uno-based relay interface to control solenoid actuated nozzles based on canopy segmentation results. Indoor trials were conducted using 15 potted Hibiscus rosa sinensis plants of varying canopy sizes to simulate a range of weed patch scenarios. The YOLO11n model achieved a mean average precision (mAP@50) of 0.98, with a precision of 0.99 and a recall close to 1.0. The YOLO11n-seg segmentation model achieved a mAP@50 of 0.48, precision of 0.55, and recall of 0.52. System performance was validated using water sensitive paper, which showed an average spray coverage of 24.22% in zones where canopy was present. An upward trend in mean spray coverage from 16.22% for small canopies to 21.46% and 21.65% for medium and large canopies, respectively, demonstrated the system's capability to adjust spray output based on canopy size in real time. These results highlight the potential of combining real time deep learning with low-cost embedded hardware for selective herbicide application. Future work will focus on expanding the detection capabilities to include three common weed species in South Dakota: water hemp (Amaranthus tuberculatus), kochia (Bassia scoparia), and foxtail (Setaria spp.), followed by further validation in both indoor and field trials within soybean and corn production systems.
Authors: Md Zahid Hasan, Guillermo Basulto-Elias, Jun Ha Chang, Sahuna Hallmark, Matthew Rizzo, Anuj Sharma, Soumik Sarkar
Abstract: We introduce scenario-based cognitive status identification in older drivers from Naturalistic driving videos and large vision models. In recent times, cognitive decline, including Alzheimer's disease (AD) and mild cognitive impairment (MCI), is often underdiagnosed due to the time-consuming and costly nature of current diagnostic methods. By analyzing real-world driving behavior captured through in-vehicle systems, this research aims to extract "digital fingerprints" that correlate with functional decline and clinical features of MCI and AD. Moreover, modern large vision models can draw meaningful insights from everyday driving patterns of older patients to early detect cognitive decline. We propose a framework that uses large vision models and naturalistic driving videos to analyze driver behavior, classify cognitive status and predict disease progression. We leverage the strong relationship between real-world driving behavior as an observation of the current cognitive status of the drivers where the vehicle can be utilized as a "diagnostic tool". Our method identifies early warning signs of functional impairment, contributing to proactive intervention strategies. This work enhances early detection and supports the development of scalable, non-invasive monitoring systems to mitigate the growing societal and economic burden of cognitive decline in the aging population.
Authors: Andrew Randono
Abstract: Diffusion models for image generation function by progressively adding noise to an image set and training a model to separate out the signal from the noise. The noise profile used by these models is white noise -- that is, noise based on independent normal distributions at each point whose mean and variance is independent of the scale. By contrast, most natural image sets exhibit a type of scale invariance in their low-order statistical properties characterized by a power-law scaling. Consequently, natural images are closer (in a quantifiable sense) to a different probability distribution that emphasizes large scale correlations and de-emphasizes small scale correlations. These scale invariant noise profiles can be incorporated into diffusion models in place of white noise to form what we will call a ``Cloud Diffusion Model". We argue that these models can lead to faster inference, improved high-frequency details, and greater controllability. In a follow-up paper, we will build and train a Cloud Diffusion Model that uses scale invariance at a fundamental level and compare it to classic, white noise diffusion models.
Authors: Giulio Federico, Fabio Carrara, Claudio Gennaro, Giuseppe Amato, Marco Di Benedetto
Abstract: Generating consistent multi-view images from a single image remains challenging. Lack of spatial consistency often degrades 3D mesh quality in surface reconstruction. To address this, we propose LoomNet, a novel multi-view diffusion architecture that produces coherent images by applying the same diffusion model multiple times in parallel to collaboratively build and leverage a shared latent space for view consistency. Each viewpoint-specific inference generates an encoding representing its own hypothesis of the novel view from a given camera pose, which is projected onto three orthogonal planes. For each plane, encodings from all views are fused into a single aggregated plane. These aggregated planes are then processed to propagate information and interpolate missing regions, combining the hypotheses into a unified, coherent interpretation. The final latent space is then used to render consistent multi-view images. LoomNet generates 16 high-quality and coherent views in just 15 seconds. In our experiments, LoomNet outperforms state-of-the-art methods on both image quality and reconstruction metrics, also showing creativity by producing diverse, plausible novel views from the same input.
Authors: Mengyao Xu, Gabriel Moreira, Ronay Ak, Radek Osmulski, Yauhen Babakhin, Zhiding Yu, Benedikt Schifferer, Even Oldridge
Abstract: Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We release two model variants, 1B and 3B. The 3B model achieves state of the art performance, scoring NDCG@5 91.0 on ViDoRe V1 and 63.5 on ViDoRe V2, placing first on both leaderboards as of June 27, 2025. Our approach leverages the NVIDIA Eagle2 Vision-Language model (VLM), modifies its architecture by replacing causal attention with bidirectional attention, and integrates a ColBERT-style late interaction mechanism to enable fine-grained multimodal retrieval in a shared embedding space. While this mechanism delivers superior retrieval accuracy, it introduces trade-offs in storage and efficiency. We provide a comprehensive analysis of these trade-offs. Additionally, we adopt a two-stage training strategy to enhance the model's retrieval capabilities.
Authors: Moseli Mots'oehli, Feimei Chen, Hok Wai Chan, Itumeleng Tlali, Thulani Babeli, Kyungim Baek, Huaijin Chen
Abstract: The scarcity of autonomous vehicle datasets from developing regions, particularly across Africa's diverse urban, rural, and unpaved roads, remains a key obstacle to robust perception in low-resource settings. We present a procedural augmentation pipeline that enhances low-cost monocular dashcam footage with realistic refractive distortions and weather-induced artifacts tailored to challenging African driving scenarios. Our refractive module simulates optical effects from low-quality lenses and air turbulence, including lens distortion, Perlin noise, Thin-Plate Spline (TPS), and divergence-free (incompressible) warps. The weather module adds homogeneous fog, heterogeneous fog, and lens flare. To establish a benchmark, we provide baseline performance using three image restoration models. To support perception research in underrepresented African contexts, without costly data collection, labeling, or simulation, we release our distortion toolkit, augmented dataset splits, and benchmark results.
Authors: Jiaxu Tian, Xuehui Yu, Yaoxing Wang, Pan Wang, Guangqian Guo, Shan Gao
Abstract: Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.
Authors: Jun-Xiong Chong, Fang-Yu Hsu, Ming-Tsung Hsu, Yi-Ting Lin, Kai-Heng Chien, Chiou-Ting Hsu, Pei-Kai Huang
Abstract: Multi-modal face anti-spoofing (FAS) aims to detect genuine human presence by extracting discriminative liveness cues from multiple modalities, such as RGB, infrared (IR), and depth images, to enhance the robustness of biometric authentication systems. However, because data from different modalities are typically captured by various camera sensors and under diverse environmental conditions, multi-modal FAS often exhibits significantly greater distribution discrepancies across training and testing domains compared to single-modal FAS. Furthermore, during the inference stage, multi-modal FAS confronts even greater challenges when one or more modalities are unavailable or inaccessible. In this paper, we propose a novel Cross-modal Transition-guided Network (CTNet) to tackle the challenges in the multi-modal FAS task. Our motivation stems from that, within a single modality, the visual differences between live faces are typically much smaller than those of spoof faces. Additionally, feature transitions across modalities are more consistent for the live class compared to those between live and spoof classes. Upon this insight, we first propose learning consistent cross-modal feature transitions among live samples to construct a generalized feature space. Next, we introduce learning the inconsistent cross-modal feature transitions between live and spoof samples to effectively detect out-of-distribution (OOD) attacks during inference. To further address the issue of missing modalities, we propose learning complementary infrared (IR) and depth features from the RGB modality as auxiliary modalities. Extensive experiments demonstrate that the proposed CTNet outperforms previous two-class multi-modal FAS methods across most protocols.
Authors: Shuai Li, Shihan Chen, Wanru Geng, Zhaohua Xu, Xiaolu Liu, Can Dong, Zhen Tian, Changlin Chen
Abstract: In the realm of industrial quality inspection, defect detection stands as a critical component, particularly in high-precision, safety-critical sectors such as automotive components aerospace, and medical devices. Traditional methods, reliant on manual inspection or early image processing algorithms, suffer from inefficiencies, high costs, and limited robustness. This paper introduces a semi-supervised defect detection framework based on conditional diffusion (DSYM), leveraging a two-stage collaborative training mechanism and a staged joint optimization strategy. The framework utilizes labeled data for initial training and subsequently incorporates unlabeled data through the generation of pseudo-labels. A conditional diffusion model synthesizes multi-scale pseudo-defect samples, while a CLIP cross-modal feature-based noise filtering mechanism mitigates label contamination. Experimental results on the NEU-DET dataset demonstrate a 78.4% mAP@0.5 with the same amount of labeled data as traditional supervised methods, and 75.1% mAP@0.5 with only 40% of the labeled data required by the original supervised model, showcasing significant advantages in data efficiency. This research provides a high-precision, low-labeling-dependent solution for defect detection in industrial quality inspection scenarios. The work of this article has been open-sourced at https://github.com/cLin-c/Semisupervised-DSYM.
Authors: Zhizhuo Pang, Zhihui Ke, Xiaobo Zhou, Tie Qiu
Abstract: Implicit neural representations for video have been recognized as a novel and promising form of video representation. Existing works pay more attention to improving video reconstruction quality but little attention to the decoding speed. However, the high computation of convolutional network used in existing methods leads to low decoding speed. Moreover, these convolution-based video representation methods also suffer from long training time, about 14 seconds per frame to achieve 35+ PSNR on Bunny. To solve the above problems, we propose GSVR, a novel 2D Gaussian-based video representation, which achieves 800+ FPS and 35+ PSNR on Bunny, only needing a training time of $2$ seconds per frame. Specifically, we propose a hybrid deformation field to model the dynamics of the video, which combines two motion patterns, namely the tri-plane motion and the polynomial motion, to deal with the coupling of camera motion and object motion in the video. Furthermore, we propose a Dynamic-aware Time Slicing strategy to adaptively divide the video into multiple groups of pictures(GOP) based on the dynamic level of the video in order to handle large camera motion and non-rigid movements. Finally, we propose quantization-aware fine-tuning to avoid performance reduction after quantization and utilize image codecs to compress Gaussians to achieve a compact representation. Experiments on the Bunny and UVG datasets confirm that our method converges much faster than existing methods and also has 10x faster decoding speed compared to other methods. Our method has comparable performance in the video interpolation task to SOTA and attains better video compression performance than NeRV.
Authors: Cheng Cui, Ting Sun, Manhui Lin, Tingquan Gao, Yubo Zhang, Jiaxuan Liu, Xueqing Wang, Zelun Zhang, Changda Zhou, Hongen Liu, Yue Zhang, Wenyu Lv, Kui Huang, Yichao Zhang, Jing Zhang, Jun Zhang, Yi Liu, Dianhai Yu, Yanjun Ma
Abstract: This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In addition to offering a high-quality OCR model library, PaddleOCR 3.0 provides efficient tools for training, inference, and deployment, supports heterogeneous hardware acceleration, and enables developers to easily build intelligent document applications.
Authors: Jingye Chen, Zhaowen Wang, Nanxuan Zhao, Li Zhang, Difan Liu, Jimei Yang, Qifeng Chen
Abstract: Graphic design is crucial for conveying ideas and messages. Designers usually organize their work into objects, backgrounds, and vectorized text layers to simplify editing. However, this workflow demands considerable expertise. With the rise of GenAI methods, an endless supply of high-quality graphic designs in pixel format has become more accessible, though these designs often lack editability. Despite this, non-layered designs still inspire human designers, influencing their choices in layouts and text styles, ultimately guiding the creation of layered designs. Motivated by this observation, we propose Accordion, a graphic design generation framework taking the first attempt to convert AI-generated designs into editable layered designs, meanwhile refining nonsensical AI-generated text with meaningful alternatives guided by user prompts. It is built around a vision language model (VLM) playing distinct roles in three curated stages. For each stage, we design prompts to guide the VLM in executing different tasks. Distinct from existing bottom-up methods (e.g., COLE and Open-COLE) that gradually generate elements to create layered designs, our approach works in a top-down manner by using the visually harmonious reference image as global guidance to decompose each layer. Additionally, it leverages multiple vision experts such as SAM and element removal models to facilitate the creation of graphic layers. We train our method using the in-house graphic design dataset Design39K, augmented with AI-generated design images coupled with refined ground truth created by a customized inpainting model. Experimental results and user studies by designers show that Accordion generates favorable results on the DesignIntention benchmark, including tasks such as text-to-template, adding text to background, and text de-rendering, and also excels in creating design variations.
Authors: Yuyang Hu, Kangfu Mei, Mojtaba Sahraee-Ardakan, Ulugbek S. Kamilov, Peyman Milanfar, Mauricio Delbracio
Abstract: Diffusion models show promise for image restoration, but existing methods often struggle with inconsistent fidelity and undesirable artifacts. To address this, we introduce Kernel Density Steering (KDS), a novel inference-time framework promoting robust, high-fidelity outputs through explicit local mode-seeking. KDS employs an $N$-particle ensemble of diffusion samples, computing patch-wise kernel density estimation gradients from their collective outputs. These gradients steer patches in each particle towards shared, higher-density regions identified within the ensemble. This collective local mode-seeking mechanism, acting as "collective wisdom", steers samples away from spurious modes prone to artifacts, arising from independent sampling or model imperfections, and towards more robust, high-fidelity structures. This allows us to obtain better quality samples at the expense of higher compute by simultaneously sampling multiple particles. As a plug-and-play framework, KDS requires no retraining or external verifiers, seamlessly integrating with various diffusion samplers. Extensive numerical validations demonstrate KDS substantially improves both quantitative and qualitative performance on challenging real-world super-resolution and image inpainting tasks.
Authors: Shaojie Bai, Seunghyeon Seo, Yida Wang, Chenghui Li, Owen Wang, Te-Li Wang, Tianyang Ma, Jason Saragih, Shih-En Wei, Nojun Kwak, Hyung Jun Kim
Abstract: Enabling photorealistic avatar animations in virtual and augmented reality (VR/AR) has been challenging because of the difficulty of obtaining ground truth state of faces. It is physically impossible to obtain synchronized images from head-mounted cameras (HMC) sensing input, which has partial observations in infrared (IR), and an array of outside-in dome cameras, which have full observations that match avatars' appearance. Prior works relying on analysis-by-synthesis methods could generate accurate ground truth, but suffer from imperfect disentanglement between expression and style in their personalized training. The reliance of extensive paired captures (HMC and dome) for the same subject makes it operationally expensive to collect large-scale datasets, which cannot be reused for different HMC viewpoints and lighting. In this work, we propose a novel generative approach, Generative HMC (GenHMC), that leverages large unpaired HMC captures, which are much easier to collect, to directly generate high-quality synthetic HMC images given any conditioning avatar state from dome captures. We show that our method is able to properly disentangle the input conditioning signal that specifies facial expression and viewpoint, from facial appearance, leading to more accurate ground truth. Furthermore, our method can generalize to unseen identities, removing the reliance on the paired captures. We demonstrate these breakthroughs by both evaluating synthetic HMC images and universal face encoders trained from these new HMC-avatar correspondences, which achieve better data efficiency and state-of-the-art accuracy.
Authors: Suoxiang Zhang, Xiaxi Li, Hongrui Chang, Zhuoyan Hou, Guoxin Wu, Ronghua Ji
Abstract: Domain-specific image generation aims to produce high-quality visual content for specialized fields while ensuring semantic accuracy and detail fidelity. However, existing methods exhibit two critical limitations: First, current approaches address prompt engineering and model adaptation separately, overlooking the inherent dependence between semantic understanding and visual representation in specialized domains. Second, these techniques inadequately incorporate domain-specific semantic constraints during content synthesis, resulting in generation outcomes that exhibit hallucinations and semantic deviations. To tackle these issues, we propose AdaptaGen, a hierarchical semantic optimization framework that integrates matrix-based prompt optimization with multi-perspective understanding, capturing comprehensive semantic relationships from both global and local perspectives. To mitigate hallucinations in specialized domains, we design a cross-modal adaptation mechanism, which, when combined with intelligent content synthesis, enables preserving core thematic elements while incorporating diverse details across images. Additionally, we introduce a two-phase caption semantic transformation during the generation phase. This approach maintains semantic coherence while enhancing visual diversity, ensuring the generated images adhere to domain-specific constraints. Experimental results confirm our approach's effectiveness, with our framework achieving superior performance across 40 categories from diverse datasets using only 16 images per category, demonstrating significant improvements in image quality, diversity, and semantic consistency.
Authors: Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Xuemeng Song, Liqiang Nie
Abstract: Composed Image Retrieval (CIR) represents a novel retrieval paradigm that is capable of expressing users' intricate retrieval requirements flexibly. It enables the user to give a multimodal query, comprising a reference image and a modification text, and subsequently retrieve the target image. Notwithstanding the considerable advances made by prevailing methodologies, CIR remains in its nascent stages due to two limitations: 1) inhomogeneity between dominant and noisy portions in visual data is ignored, leading to query feature degradation, and 2) the priority of textual data in the image modification process is overlooked, which leads to a visual focus bias. To address these two limitations, this work presents a focus mapping-based feature extractor, which consists of two modules: dominant portion segmentation and dual focus mapping. It is designed to identify significant dominant portions in images and guide the extraction of visual and textual data features, thereby reducing the impact of noise interference. Subsequently, we propose a textually guided focus revision module, which can utilize the modification requirements implied in the text to perform adaptive focus revision on the reference image, thereby enhancing the perception of the modification focus on the composed features. The aforementioned modules collectively constitute the segmentatiOn-based Focus shiFt reviSion nETwork (\mbox{OFFSET}), and comprehensive experiments on four benchmark datasets substantiate the superiority of our proposed method. The codes and data are available on https://zivchen-ty.github.io/OFFSET.github.io/
Authors: Junfei Shi, Yu Cheng, Haiyan Jin, Junhuai Li, Zhaolin Xiao, Maoguo Gong, Weisi Lin
Abstract: Diffusion models have demonstrated exceptional performance across various domains due to their ability to model and generate complicated data distributions. However, when applied to PolSAR data, traditional real-valued diffusion models face challenges in capturing complex-valued phase information.Moreover, these models often struggle to preserve fine structural details. To address these limitations, we leverage the Contourlet transform, which provides rich multiscale and multidirectional representations well-suited for PolSAR imagery. We propose a structural knowledge-guided complex diffusion model for PolSAR image classification in the Contourlet domain. Specifically, the complex Contourlet transform is first applied to decompose the data into low- and high-frequency subbands, enabling the extraction of statistical and boundary features. A knowledge-guided complex diffusion network is then designed to model the statistical properties of the low-frequency components. During the process, structural information from high-frequency coefficients is utilized to guide the diffusion process, improving edge preservation. Furthermore, multiscale and multidirectional high-frequency features are jointly learned to further boost classification accuracy. Experimental results on three real-world PolSAR datasets demonstrate that our approach surpasses state-of-the-art methods, particularly in preserving edge details and maintaining region homogeneity in complex terrain.
Authors: Jiahui Wang, Qin Xu, Bo Jiang, Bin Luo
Abstract: Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of maintaining strong generalization abilities, particularly towards unseen new classes. This limitation partly arises from these methods treating all tokens of the image and text encoder equally, which can lead to overfitting on less informative features (e.g., background noise, template words) and degrade the general representations that are crucial for novel concept recognition. To address this issue, we propose Dynamic Rank Adaptation (DRA), a novel adapter variant method, designed specifically to enhance new class generalization. DRA dynamically allocates adaptation ranks based on the importance of features during training to preserve general knowledge. DRA first employs token importance grouping, using sequence attention to evaluate and group tokens by their importance. Then, we adopt rank adaptation according to the importance of each token group dynamically by assigning higher feature ranks to the more important tokens. Also, we design a new channel response mechanism to prioritize the preservation and adaptation of feature channels identified as the most informative for each instance. In addition, a L1 regularization term is introduced to stabilize the training. Extensive experiments demonstrate the effectiveness and superiority of our proposed DRA over existing works, especially on enhancing the performance of new classes on various benchmarks, including base-new classes, cross-datasets evaluation and domain generalization. The source code will be published after the paper is received.
Authors: Omar Zamzam, Haleh Akrami, Anand Joshi, Richard Leahy
Abstract: Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas. This broad definition of brain lesions includes areas of the brain that are irreversibly damaged, as well as areas of brain tissue that are deformed as a result of lesion growth or swelling. Despite the importance of differentiating between damaged and deformed tissue, existing lesion segmentation methods overlook this distinction, labeling both of them as a single anomaly. In this work, we introduce a diffusion model-based framework for analyzing and reversing the brain lesion process. Our pipeline first segments abnormal regions in the brain, then estimates and reverses tissue deformations by restoring displaced tissue to its original position, isolating the core lesion area representing the initial damage. Finally, we inpaint the core lesion area to arrive at an estimation of the pre-lesion healthy brain. This proposed framework reverses a forward lesion growth process model that is well-established in biomechanical studies that model brain lesions. Our results demonstrate improved accuracy in lesion segmentation, characterization, and brain labeling compared to traditional methods, offering a robust tool for clinical and research applications in brain lesion analysis. Since pre-lesion healthy versions of abnormal brains are not available in any public dataset for validation of the reverse process, we simulate a forward model to synthesize multiple lesioned brain images.
Authors: Joonhyung Park, Peng Tang, Sagnik Das, Srikar Appalaraju, Kunwar Yashraj Singh, R. Manmatha, Shabnam Ghadar
Abstract: Visual agent models for automating human activities on Graphical User Interfaces (GUIs) have emerged as a promising research direction, driven by advances in large Vision Language Models (VLMs). A critical challenge in GUI automation is the precise grounding of interface elements across diverse platforms. Existing vision-only GUI agents directly ground elements from large and cluttered screenshots, requiring them to process substantial irrelevant information that compromises their accuracy. In addition, these approaches typically employ basic cross-entropy loss for learning grounding objectives, which fails to effectively capture grounding quality compared to established object detection metrics like Intersection-over-Union (IoU). To address these issues, we introduce R-VLM, a novel GUI grounding approach that leverages zoomed-in region proposals for precise element localization. We also propose an IoU-aware objective function that facilitates model convergence toward high IoU predictions. Our approach bridges the gap between VLMs and conventional object detection techniques, improving the state-of-the-art grounding accuracy by 13% across diverse GUI platforms on the GUI grounding benchmarks ScreenSpot and AgentStudio. In addition, our R-VLM approach shows 3.2-9.7% absolute accuracy improvements in GUI navigation tasks on the AITW and Mind2Web benchmarks.
Authors: Rongsheng Wang, Junying Chen, Ke Ji, Zhenyang Cai, Shunian Chen, Yunjin Yang, Benyou Wang
Abstract: Recent advances in video generation have shown remarkable progress in open-domain settings, yet medical video generation remains largely underexplored. Medical videos are critical for applications such as clinical training, education, and simulation, requiring not only high visual fidelity but also strict medical accuracy. However, current models often produce unrealistic or erroneous content when applied to medical prompts, largely due to the lack of large-scale, high-quality datasets tailored to the medical domain. To address this gap, we introduce MedVideoCap-55K, the first large-scale, diverse, and caption-rich dataset for medical video generation. It comprises over 55,000 curated clips spanning real-world medical scenarios, providing a strong foundation for training generalist medical video generation models. Built upon this dataset, we develop MedGen, which achieves leading performance among open-source models and rivals commercial systems across multiple benchmarks in both visual quality and medical accuracy. We hope our dataset and model can serve as a valuable resource and help catalyze further research in medical video generation. Our code and data is available at https://github.com/FreedomIntelligence/MedGen
Authors: Jiahui Wang, Qin Xu, Bo Jiang, Bin Luo
Abstract: Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or image instructions in fine-tuning VLMs. However, most existing works ignore the structural relationships between learnable prompts and tokens within and between modalities. Moreover, balancing the performance of base and new classes remains a significant challenge. In this paper, we propose an Integrated Structural Prompt (ISP) for VLMs to enhance the interaction of information representations between the text and image branches. ISP introduces self-structural and cross-structural prompt modules to model the structural relationships between learnable prompts and frozen tokens within and across modalities. This enables efficient information transfer while preserving feature stability. Additionally, we propose a sample probing module that dynamically adjusts loss coefficients based on sample difficulty, preventing the mode from overfitting to simple samples and improving generalization ability to new classes. Extensive experiments on three widely used settings: base-to-new generalization, cross-dataset evaluation, and domain generalization demonstrate that the proposed ISP achieves competitive performance against state-of-the-art methods.
Authors: Yisu Zhang, Chenjie Cao, Chaohui Yu, Jianke Zhu
Abstract: Video Diffusion Models (VDMs) have demonstrated remarkable capabilities in synthesizing realistic videos by learning from large-scale data. Although vanilla Low-Rank Adaptation (LoRA) can learn specific spatial or temporal movement to driven VDMs with constrained data, achieving precise control over both camera trajectories and object motion remains challenging due to the unstable fusion and non-linear scalability. To address these issues, we propose LiON-LoRA, a novel framework that rethinks LoRA fusion through three core principles: Linear scalability, Orthogonality, and Norm consistency. First, we analyze the orthogonality of LoRA features in shallow VDM layers, enabling decoupled low-level controllability. Second, norm consistency is enforced across layers to stabilize fusion during complex camera motion combinations. Third, a controllable token is integrated into the diffusion transformer (DiT) to linearly adjust motion amplitudes for both cameras and objects with a modified self-attention mechanism to ensure decoupled control. Additionally, we extend LiON-LoRA to temporal generation by leveraging static-camera videos, unifying spatial and temporal controllability. Experiments demonstrate that LiON-LoRA outperforms state-of-the-art methods in trajectory control accuracy and motion strength adjustment, achieving superior generalization with minimal training data. Project Page: https://fuchengsu.github.io/lionlora.github.io/
Authors: Mohsi Jawaid, Marcus M\"artens, Tat-Jun Chin
Abstract: Spacecraft pose estimation is crucial for autonomous in-space operations, such as rendezvous, docking and on-orbit servicing. Vision-based pose estimation methods, which typically employ RGB imaging sensors, is a compelling solution for spacecraft pose estimation, but are challenged by harsh lighting conditions, which produce imaging artifacts such as glare, over-exposure, blooming and lens flare. Due to their much higher dynamic range, neuromorphic or event sensors are more resilient to extreme lighting conditions. However, event sensors generally have lower spatial resolution and suffer from reduced signal-to-noise ratio during periods of low relative motion. This work addresses these individual sensor limitations by introducing a sensor fusion approach combining RGB and event sensors. A beam-splitter prism was employed to achieve precise optical and temporal alignment. Then, a RANSAC-based technique was developed to fuse the information from the RGB and event channels to achieve pose estimation that leveraged the strengths of the two modalities. The pipeline was complemented by dropout uncertainty estimation to detect extreme conditions that affect either channel. To benchmark the performance of the proposed event-RGB fusion method, we collected a comprehensive real dataset of RGB and event data for satellite pose estimation in a laboratory setting under a variety of challenging illumination conditions. Encouraging results on the dataset demonstrate the efficacy of our event-RGB fusion approach and further supports the usage of event sensors for spacecraft pose estimation. To support community research on this topic, our dataset will be released publicly.
Authors: Aayushma Pant, Arbind Agrahari Baniya, Tsz-Kwan Lee, Sunil Aryal
Abstract: Hyperspectral images are high-dimensional datasets consisting of hundreds of contiguous spectral bands, enabling detailed material and surface analysis. Hyperspectral anomaly detection (HAD) refers to the technique of identifying and locating anomalous targets in such data without prior information about a hyperspectral scene or target spectrum. This technology has seen rapid advancements in recent years, with applications in agriculture, defence, military surveillance, and environmental monitoring. Despite this significant progress, existing HAD methods continue to face challenges such as high computational complexity, sensitivity to noise, and limited generalisation across diverse datasets. This study presents a comprehensive comparison of various HAD techniques, categorising them into statistical models, representation-based methods, classical machine learning approaches, and deep learning models. We evaluated these methods across 17 benchmarking datasets using different performance metrics, such as ROC, AUC, and separability map to analyse detection accuracy, computational efficiency, their strengths, limitations, and directions for future research.The research shows that deep learning models achieved the highest detection accuracy, while statistical models demonstrated exceptional speed across all datasets. This study aims to provide valuable insights for researchers and practitioners working to advance the field of hyperspectral anomaly detection methods.
Authors: Yegyu Han, Taegyoon Yoon, Dayeon Woo, Sojeong Kim, Hyung-Sin Kim
Abstract: Recent advances on 6D object-pose estimation has achieved high performance on representative benchmarks such as LM-O, YCB-V, and T-Less. However, these datasets were captured under fixed illumination and camera settings, leaving the impact of real-world variations in illumination, exposure, gain or depth-sensor mode - and the potential of test-time sensor control to mitigate such variations - largely unexplored. To bridge this gap, we introduce SenseShift6D, the first RGB-D dataset that physically sweeps 13 RGB exposures, 9 RGB gains, auto-exposure, 4 depth-capture modes, and 5 illumination levels. For three common household objects (spray, pringles, and tincase), we acquire 101.9k RGB and 10k depth images, which can provide 1,380 unique sensor-lighting permutations per object pose. Experiments with state-of-the-art models on our dataset show that applying sensor control during test-time induces greater performance improvement over digital data augmentation, achieving performance comparable to or better than costly increases in real-world training data quantity and diversity. Adapting either RGB or depth sensors individually is effective, while jointly adapting multimodal RGB-D configurations yields even greater improvements. SenseShift6D extends the 6D-pose evaluation paradigm from data-centered to sensor-aware robustness, laying a foundation for adaptive, self-tuning perception systems capable of operating robustly in uncertain real-world environments. Our dataset is available at: huggingface.co/datasets/Yegyu/SenseShift6D Associated scripts can be found at: github.com/yegyu-han/SenseShift6D
Authors: Radoslaw Roszczyk, Artur Krupa, Izabella Antoniuk
Abstract: The acquisition of accurately coloured, balanced images in an optical microscope can be a challenge even for experienced microscope operators. This article presents an entirely automatic mechanism for balancing the white level that allows the correction of the microscopic colour images adequately. The results of the algorithm have been confirmed experimentally on a set of two hundred microscopic images. The images contained scans of three microscopic specimens commonly used in pathomorphology. Also, the results achieved were compared with other commonly used white balance algorithms in digital photography. The algorithm applied in this work is more effective than the classical algorithms used in colour photography for microscopic images stained with hematoxylin-phloxine-saffron and for immunohistochemical staining images.
Authors: Ruijie Lu, Yu Liu, Jiaxiang Tang, Junfeng Ni, Yuxiang Wang, Diwen Wan, Gang Zeng, Yixin Chen, Siyuan Huang
Abstract: Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting part decomposition and articulation modeling. Meanwhile, neural reconstruction approaches (e.g., NeRF or Gaussian Splatting) rely on dense multi-view or interaction data, limiting their scalability. In this paper, we introduce DreamArt, a novel framework for generating high-fidelity, interactable articulated assets from single-view images. DreamArt employs a three-stage pipeline: firstly, it reconstructs part-segmented and complete 3D object meshes through a combination of image-to-3D generation, mask-prompted 3D segmentation, and part amodal completion. Second, we fine-tune a video diffusion model to capture part-level articulation priors, leveraging movable part masks as prompt and amodal images to mitigate ambiguities caused by occlusion. Finally, DreamArt optimizes the articulation motion, represented by a dual quaternion, and conducts global texture refinement and repainting to ensure coherent, high-quality textures across all parts. Experimental results demonstrate that DreamArt effectively generates high-quality articulated objects, possessing accurate part shape, high appearance fidelity, and plausible articulation, thereby providing a scalable solution for articulated asset generation. Our project page is available at https://dream-art-0.github.io/DreamArt/.
Authors: Yujie Hu, Xuanyu Zhang, Weiqi Li, Jian Zhang
Abstract: Virtual try-on has made significant progress in recent years. This paper addresses how to achieve multifunctional virtual try-on guided solely by text instructions, including full outfit change and local editing. Previous methods primarily relied on end-to-end networks to perform single try-on tasks, lacking versatility and flexibility. We propose TalkFashion, an intelligent try-on assistant that leverages the powerful comprehension capabilities of large language models to analyze user instructions and determine which task to execute, thereby activating different processing pipelines accordingly. Additionally, we introduce an instruction-based local repainting model that eliminates the need for users to manually provide masks. With the help of multi-modal models, this approach achieves fully automated local editings, enhancing the flexibility of editing tasks. The experimental results demonstrate better semantic consistency and visual quality compared to the current methods.
Authors: Xin Hu, Ke Qin, Guiduo Duan, Ming Li, Yuan-Fang Li, Tao He
Abstract: Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes. Although recent approaches leveraging pre-trained vision-language models (VLMs) have significantly improved performance in the open-vocabulary setting, they commonly ignore the inherent limitations of VLMs in spatial relation reasoning, such as difficulty in distinguishing object relative positions, which results in suboptimal relation prediction. Motivated by the denoising diffusion model's inversion process in preserving the spatial structure of input images, we propose SPADE (SPatial-Aware Denoising-nEtwork) framework -- a novel approach for open-vocabulary PSG. SPADE consists of two key steps: (1) inversion-guided calibration for the UNet adaptation, and (2) spatial-aware context reasoning. In the first step, we calibrate a general pre-trained teacher diffusion model into a PSG-specific denoising network with cross-attention maps derived during inversion through a lightweight LoRA-based fine-tuning strategy. In the second step, we develop a spatial-aware relation graph transformer that captures both local and long-range contextual information, facilitating the generation of high-quality relation queries. Extensive experiments on benchmark PSG and Visual Genome datasets demonstrate that SPADE outperforms state-of-the-art methods in both closed- and open-set scenarios, particularly for spatial relationship prediction.
Authors: Xin Li, Mingming Gong, Yunfei Wu, Jianxin Dai, Antai Guo, Xinghua Jiang, Haoyu Cao, Yinsong Liu, Deqiang Jiang, Xing Sun
Abstract: Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document understanding models to generate predictions on distinct subtasks, subsequently integrating their results into a holistic document reconstruction format via heuristic principles. Nevertheless, these multi-stage methodologies are hindered by the phenomenon of error propagation, resulting in suboptimal performance. Furthermore, contemporary studies utilize generative models to extract the logical sequence of plain text, tables and mathematical expressions in an end-to-end process. However, this approach is deficient in preserving the information related to element layouts, which are vital for document reconstruction. To surmount these aforementioned limitations, we in this paper present an innovative autoregressive model specifically designed for document reconstruction, referred to as Document Reconstruction via End-to-end Autoregressive Model (DREAM). DREAM transmutes the text image into a sequence of document reconstruction in a comprehensive, end-to-end process, encapsulating a broader spectrum of document element information. In addition, we establish a standardized definition of the document reconstruction task, and introduce a novel Document Similarity Metric (DSM) and DocRec1K dataset for assessing the performance of the task. Empirical results substantiate that our methodology attains unparalleled performance in the realm of document reconstruction. Furthermore, the results on a variety of subtasks, encompassing document layout analysis, text recognition, table structure recognition, formula recognition and reading order detection, indicate that our model is competitive and compatible with various tasks.
Authors: Samed Do\u{g}an, Maximilian Hoh, Nico Leuze, Nicolas R. -Pe\~na, Alfred Sch\"ottl
Abstract: The development of safe and robust autonomous driving functions is heavily dependent on large-scale, high-quality sensor data. However, real-word data acquisition demands intensive human labor and is strongly limited by factors such as labeling cost, driver safety protocols and diverse scenario coverage. Thus, multiple lines of work focus on the conditional generation of synthetic camera sensor data. We identify a significant gap in research regarding daytime variation, presumably caused by the scarcity of available labels. Consequently, we present the solar altitude as global conditioning variable. It is readily computable from latitude-longitude coordinates and local time, eliminating the need for extensive manual labeling. Our work is complemented by a tailored normalization approach, targeting the sensitivity of daylight towards small numeric changes in altitude. We demonstrate its ability to accurately capture lighting characteristics and illumination-dependent image noise in the context of diffusion models.
Authors: Wang Wang, Mingyu Shi, Jun Jiang, Wenqian Ma, Chong Liu, Yasutaka Narazaki, Xuguang Wang
Abstract: As critical transportation infrastructure, bridges face escalating challenges from aging and deterioration, while traditional manual inspection methods suffer from low efficiency. Although 3D point cloud technology provides a new data-driven paradigm, its application potential is often constrained by the incompleteness of real-world data, which results from missing labels and scanning occlusions. To overcome the bottleneck of insufficient generalization in existing synthetic data methods, this paper proposes a systematic framework for generating 3D bridge data. This framework can automatically generate complete point clouds featuring component-level instance annotations, high-fidelity color, and precise normal vectors. It can be further extended to simulate the creation of diverse and physically realistic incomplete point clouds, designed to support the training of segmentation and completion networks, respectively. Experiments demonstrate that a PointNet++ model trained with our synthetic data achieves a mean Intersection over Union (mIoU) of 84.2% in real-world bridge semantic segmentation. Concurrently, a fine-tuned KT-Net exhibits superior performance on the component completion task. This research offers an innovative methodology and a foundational dataset for the 3D visual analysis of bridge structures, holding significant implications for advancing the automated management and maintenance of infrastructure.
Authors: Yuhuan Xie, Aoxuan Pan, Ming-Xian Lin, Wei Huang, Yi-Hua Huang, Xiaojuan Qi
Abstract: Generative models have achieved significant progress in advancing 2D image editing, demonstrating exceptional precision and realism. However, they often struggle with consistency and object identity preservation due to their inherent pixel-manipulation nature. To address this limitation, we introduce a novel "2D-3D-2D" framework. Our approach begins by lifting 2D objects into 3D representation, enabling edits within a physically plausible, rigidity-constrained 3D environment. The edited 3D objects are then reprojected and seamlessly inpainted back into the original 2D image. In contrast to existing 2D editing methods, such as DragGAN and DragDiffusion, our method directly manipulates objects in a 3D environment. Extensive experiments highlight that our framework surpasses previous methods in general performance, delivering highly consistent edits while robustly preserving object identity.
Authors: L'ea Dubois, Klaus Schmidt, Chengyu Wang, Ji-Hoon Park, Lin Wang, Santiago Munoz
Abstract: Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To bridge this cognitive gap, we propose a novel framework that synergistically fuses a powerful Vision Foundation Model (VFM) for deep visual perception with a Large Language Model (LLM) serving as a knowledge-driven reasoning core. Our key technical innovation is a sophisticated fusion module, inspired by the Q-Former architecture, which distills complex spatiotemporal and object-centric visual features into a concise, language-aligned representation. This enables the LLM to effectively ground its inferential processes in direct visual evidence. The model is trained via a two-stage strategy, beginning with large-scale alignment pre-training on video-text data, followed by targeted instruction fine-tuning on a curated dataset designed to elicit advanced reasoning and prediction skills. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple challenging benchmarks. Notably, it exhibits remarkable zero-shot generalization to unseen reasoning tasks, and our in-depth ablation studies validate the critical contribution of each architectural component. This work pushes the boundary of machine perception from simple recognition towards genuine cognitive understanding, paving the way for more intelligent and capable AI systems in robotics, human-computer interaction, and beyond.
Authors: Ourui Fu, Hangzhou He, Xinliang Zhang, Lei Zhu, Shuang Zeng, ZhaoHeng Xie, Yanye Lu
Abstract: The annotation bottleneck in semantic segmentation has driven significant interest in few-shot segmentation, which aims to develop segmentation models capable of generalizing rapidly to novel classes using minimal exemplars. Conventional training paradigms typically generate query prior maps by extracting masked-area features from support images, followed by making predictions guided by these prior maps. However, current approaches remain constrained by two critical limitations stemming from inter- and intra-image discrepancies, both of which significantly degrade segmentation performance: 1) The semantic gap between support and query images results in mismatched features and inaccurate prior maps; 2) Visually similar yet semantically distinct regions within support or query images lead to false negative or false positive predictions. We propose a novel FSS method called \textbf{I$^2$R}: 1) Using category-specific high level representations which aggregate global semantic cues from support and query images, enabling more precise inter-image region localization and address the first limitation. 2) Directional masking strategy that suppresses inconsistent support-query pixel pairs, which exhibit high feature similarity but conflicting mask, to mitigate the second issue. Experiments demonstrate that our method outperforms state-of-the-art approaches, achieving improvements of 1.9\% and 2.1\% in mIoU under the 1-shot setting on PASCAL-5$^i$ and COCO-20$^i$ benchmarks, respectively.
Authors: Yue Peng, Bing Xiong, Fuqiang Chen, De Eybo, RanRan Zhang, Wanming Hu, Jing Cai, Wenjian Qin
Abstract: Immunohistochemical (IHC) virtual staining is a task that generates virtual IHC images from H\&E images while maintaining pathological semantic consistency with adjacent slices. This task aims to achieve cross-domain mapping between morphological structures and staining patterns through generative models, providing an efficient and cost-effective solution for pathological analysis. However, under weakly paired conditions, spatial heterogeneity between adjacent slices presents significant challenges. This can lead to inaccurate one-to-many mappings and generate results that are inconsistent with the pathological semantics of adjacent slices. To address this issue, we propose a novel unbalanced self-information feature transport for IHC virtual staining, named USIGAN, which extracts global morphological semantics without relying on positional correspondence.By removing weakly paired terms in the joint marginal distribution, we effectively mitigate the impact of weak pairing on joint distributions, thereby significantly improving the content consistency and pathological semantic consistency of the generated results. Moreover, we design the Unbalanced Optimal Transport Consistency (UOT-CTM) mechanism and the Pathology Self-Correspondence (PC-SCM) mechanism to construct correlation matrices between H\&E and generated IHC in image-level and real IHC and generated IHC image sets in intra-group level.. Experiments conducted on two publicly available datasets demonstrate that our method achieves superior performance across multiple clinically significant metrics, such as IoD and Pearson-R correlation, demonstrating better clinical relevance.
Authors: Juli Zhang, Zeyu Yan, Jing Zhang, Qiguang Miao, Quan Wang
Abstract: Accurate remote sensing-based crop yield prediction remains a fundamental challenging task due to complex spatial patterns, heterogeneous spectral characteristics, and dynamic agricultural conditions. Existing methods often suffer from limited spatial modeling capacity, weak generalization across crop types and years. To address these challenges, we propose DFYP, a novel Dynamic Fusion framework for crop Yield Prediction, which combines spectral channel attention, edge-adaptive spatial modeling and a learnable fusion mechanism to improve robustness across diverse agricultural scenarios. Specifically, DFYP introduces three key components: (1) a Resolution-aware Channel Attention (RCA) module that enhances spectral representation by adaptively reweighting input channels based on resolution-specific characteristics; (2) an Adaptive Operator Learning Network (AOL-Net) that dynamically selects operators for convolutional kernels to improve edge-sensitive spatial feature extraction under varying crop and temporal conditions; and (3) a dual-branch architecture with a learnable fusion mechanism, which jointly models local spatial details and global contextual information to support cross-resolution and cross-crop generalization. Extensive experiments on multi-year datasets MODIS and multi-crop dataset Sentinel-2 demonstrate that DFYP consistently outperforms current state-of-the-art baselines in RMSE, MAE, and R2 across different spatial resolutions, crop types, and time periods, showcasing its effectiveness and robustness for real-world agricultural monitoring.
Authors: Wenkang Zhang, Yan Zhao, Qiang Wang, Li Song, Zhengxue Cheng
Abstract: Free-viewpoint video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representations remains a major challenge. Recent advances in 3D Gaussian Splatting (3DGS) and its dynamic extensions have enabled high-fidelity scene modeling. However, existing methods often couple scene reconstruction with optimization-dependent coding, which limits generalizability. This paper presents Feedforward Compression of Dynamic Gaussian Splatting (D-FCGS), a novel feedforward framework for compressing temporally correlated Gaussian point cloud sequences. Our approach introduces a Group-of-Frames (GoF) structure with I-P frame coding, where inter-frame motions are extracted via sparse control points. The resulting motion tensors are compressed in a feedforward manner using a dual prior-aware entropy model that combines hyperprior and spatial-temporal priors for accurate rate estimation. For reconstruction, we perform control-point-guided motion compensation and employ a refinement network to enhance view-consistent fidelity. Trained on multi-view video-derived Gaussian frames, D-FCGS generalizes across scenes without per-scene optimization. Experiments show that it matches the rate-distortion performance of optimization-based methods, achieving over 40 times compression in under 2 seconds while preserving visual quality across viewpoints. This work advances feedforward compression for dynamic 3DGS, paving the way for scalable FVV transmission and storage in immersive applications.
Authors: Xianzhi Ma, Jianhui Li, Changhua Pei, Hao Liu
Abstract: The application of Vision-Language Models (VLMs) in remote sensing (RS) image understanding has achieved notable progress, demonstrating the basic ability to recognize and describe geographical entities. However, existing RS-VLMs are mostly limited to image-level and region-level tasks, lacking the capability to handle pixel-level tasks and performing poorly in small-object recognition scenarios. Moreover, RS-VLMs consume significant computational resources when processing high-resolution RS images, further restricting their practical applicability. In this context, we propose GeoMag (Geographical Magnifier), an end-to-end general-purpose large model framework for RS. GeoMag dynamically focuses the attention scope based on prompt semantics to effectively perform remote sensing image parsing across multiple levels of granularity. This method introduces Task-driven Multi-granularity Resolution Adjustment (TMRA) and Prompt-guided Semantic-aware Cropping (PSC), which adaptively reduce the spatial resolution of task-irrelevant regions while enhancing the visual representation of task-relevant areas. This approach improves the model's perception of critical target regions, suppresses background redundancy, and reduces the computational cost of interpreting high-resolution RS imagery. Extensive comparative experiments on 10 benchmarks demonstrate that GeoMag not only excels in handling pixel-level tasks but also maintains competitive performance across tasks of other granularities compared to existing RS-VLMs.
Authors: Yuedong Tan, Jiawei Shao, Eduard Zamfir, Ruanjun Li, Zhaochong An, Chao Ma, Danda Paudel, Luc Van Gool, Radu Timofte, Zongwei Wu
Abstract: Multimodal data is known to be helpful for visual tracking by improving robustness to appearance variations. However, sensor synchronization challenges often compromise data availability, particularly in video settings where shortages can be temporal. Despite its importance, this area remains underexplored. In this paper, we present the first comprehensive study on tracker performance with temporally incomplete multimodal data. Unsurprisingly, under such a circumstance, existing trackers exhibit significant performance degradation, as their rigid architectures lack the adaptability needed to effectively handle missing modalities. To address these limitations, we propose a flexible framework for robust multimodal tracking. We venture that a tracker should dynamically activate computational units based on missing data rates. This is achieved through a novel Heterogeneous Mixture-of-Experts fusion mechanism with adaptive complexity, coupled with a video-level masking strategy that ensures both temporal consistency and spatial completeness which is critical for effective video tracking. Surprisingly, our model not only adapts to varying missing rates but also adjusts to scene complexity. Extensive experiments show that our model achieves SOTA performance across 9 benchmarks, excelling in both conventional complete and missing modality settings. The code and benchmark will be publicly available at https://github.com/supertyd/FlexTrack/tree/main.
Authors: Jonas Klotz, Tom Burgert, Beg\"um Demir
Abstract: The development of explainable artificial intelligence (xAI) methods for scene classification problems has attracted great attention in remote sensing (RS). Most xAI methods and the related evaluation metrics in RS are initially developed for natural images considered in computer vision (CV), and their direct usage in RS may not be suitable. To address this issue, in this paper, we investigate the effectiveness of explanation methods and metrics in the context of RS image scene classification. In detail, we methodologically and experimentally analyze ten explanation metrics spanning five categories (faithfulness, robustness, localization, complexity, randomization), applied to five established feature attribution methods (Occlusion, LIME, GradCAM, LRP, and DeepLIFT) across three RS datasets. Our methodological analysis identifies key limitations in both explanation methods and metrics. The performance of perturbation-based methods, such as Occlusion and LIME, heavily depends on perturbation baselines and spatial characteristics of RS scenes. Gradient-based approaches like GradCAM struggle when multiple labels are present in the same image, while some relevance propagation methods (LRP) can distribute relevance disproportionately relative to the spatial extent of classes. Analogously, we find limitations in evaluation metrics. Faithfulness metrics share the same problems as perturbation-based methods. Localization metrics and complexity metrics are unreliable for classes with a large spatial extent. In contrast, robustness metrics and randomization metrics consistently exhibit greater stability. Our experimental results support these methodological findings. Based on our analysis, we provide guidelines for selecting explanation methods, metrics, and hyperparameters in the context of RS image scene classification.
Authors: Xinyu Huang, Yuhao Dong, Weiwei Tian, Bo Li, Rui Feng, Ziwei Liu
Abstract: State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. In this paper, we propose Multi-turn Grounding-based Policy Optimization (MGPO), an end-to-end reinforcement learning (RL) framework that enables LMMs to iteratively focus on key visual regions by automatically cropping sub-images, based on model-predicted grounding coordinates within a multi-turn conversation framework. Compared to supervised fine-tuning (SFT), which requires costly additional grounding annotations, our approach highlights that LMMs can emerge robust grounding abilities during the RL training process, leveraging only a binary reward function derived from the correctness of the final answer. Additionally, we observe that LMMs struggle to autonomously trigger visual grounding during the rollout process. To address this cold start problem, we design a multi-turn conversational template and restrict policy loss computation to model outputs generated across multiple dialogue rounds, thereby promoting stable optimization. Extensive experiments demonstrate that, when trained on standard visual-question-short answering data without grounding annotations, MGPO effectively elicits stronger grounding capabilities compared to GRPO, leading to 5.4\% improvement on in-distribution MME-Realworld and 5.2\% improvement on the challenging out-of-distribution (OOD) V* Bench. Notably, MGPO post-training on Qwen2.5-VL-7B with 21K samples surpasses OpenAI's o1 and GPT-4o models on the OOD V* Bench. Codes are available at https://github.com/EvolvingLMMs-Lab/MGPO.
Authors: Quanzhu Niu, Yikang Zhou, Shihao Chen, Tao Zhang, Shunping Ji
Abstract: Video Instance Segmentation (VIS) fundamentally struggles with pervasive challenges including object occlusions, motion blur, and appearance variations during temporal association. To overcome these limitations, this work introduces geometric awareness to enhance VIS robustness by strategically leveraging monocular depth estimation. We systematically investigate three distinct integration paradigms. Expanding Depth Channel (EDC) method concatenates the depth map as input channel to segmentation networks; Sharing ViT (SV) designs a uniform ViT backbone, shared between depth estimation and segmentation branches; Depth Supervision (DS) makes use of depth prediction as an auxiliary training guide for feature learning. Though DS exhibits limited effectiveness, benchmark evaluations demonstrate that EDC and SV significantly enhance the robustness of VIS. When with Swin-L backbone, our EDC method gets 56.2 AP, which sets a new state-of-the-art result on OVIS benchmark. This work conclusively establishes depth cues as critical enablers for robust video understanding.
Authors: Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Hieu Le, Pascal Fua
Abstract: Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However, the dense representation does not scale well to increasing voxel resolutions, severely limiting the reconstruction quality. We thus present a sparse representation method, that maximizes memory efficiency and enables significantly higher resolution reconstructions on standard hardware. We implement this through a two-stage approach: First training a network to predict voxel occupancies from posed images and associated depth maps, then computing features and performing volume rendering only in voxels with sufficiently high occupancy estimates. To support this sparse representation, we developed custom algorithms for efficient sampling, feature aggregation, and querying from sparse volumes-overcoming the dense-volume assumptions inherent in existing works. Experiments on public datasets demonstrate that our approach reduces storage requirements by more than 50 times without performance degradation, enabling reconstructions at $512^3$ resolution compared to the typical $128^3$ on similar hardware, and achieving superior reconstruction accuracy over current state-of-the-art methods.
Authors: Zhenghao Zhang, Junchao Liao, Xiangyu Meng, Long Qin, Weizhi Wang
Abstract: Recent advances in diffusion transformer models for motion-guided video generation, such as Tora, have shown significant progress. In this paper, we present Tora2, an enhanced version of Tora, which introduces several design improvements to expand its capabilities in both appearance and motion customization. Specifically, we introduce a decoupled personalization extractor that generates comprehensive personalization embeddings for multiple open-set entities, better preserving fine-grained visual details compared to previous methods. Building on this, we design a gated self-attention mechanism to integrate trajectory, textual description, and visual information for each entity. This innovation significantly reduces misalignment in multimodal conditioning during training. Moreover, we introduce a contrastive loss that jointly optimizes trajectory dynamics and entity consistency through explicit mapping between motion and personalization embeddings. Tora2 is, to our best knowledge, the first method to achieve simultaneous multi-entity customization of appearance and motion for video generation. Experimental results demonstrate that Tora2 achieves competitive performance with state-of-the-art customization methods while providing advanced motion control capabilities, which marks a critical advancement in multi-condition video generation. Project page: https://ali-videoai.github.io/Tora2_page/.
Authors: Vera Soboleva, Aibek Alanov, Andrey Kuznetsov, Konstantin Sobolev
Abstract: While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization capability and output diversity. This paper tackles the challenging yet most impactful task of adapting a diffusion model using just a single concept image, as single-image customization holds the greatest practical potential. We introduce T-LoRA, a Timestep-Dependent Low-Rank Adaptation framework specifically designed for diffusion model personalization. In our work we show that higher diffusion timesteps are more prone to overfitting than lower ones, necessitating a timestep-sensitive fine-tuning strategy. T-LoRA incorporates two key innovations: (1) a dynamic fine-tuning strategy that adjusts rank-constrained updates based on diffusion timesteps, and (2) a weight parametrization technique that ensures independence between adapter components through orthogonal initialization. Extensive experiments show that T-LoRA and its individual components outperform standard LoRA and other diffusion model personalization techniques. They achieve a superior balance between concept fidelity and text alignment, highlighting the potential of T-LoRA in data-limited and resource-constrained scenarios. Code is available at https://github.com/ControlGenAI/T-LoRA.
Authors: Haiwen Li, Delong Liu, Zhaohui Hou, Zhicheng Zhao, Fei Su
Abstract: As a challenging vision-language (VL) task, Composed Image Retrieval (CIR) aims to retrieve target images using multimodal (image+text) queries. Although many existing CIR methods have attained promising performance, their reliance on costly, manually labeled triplets hinders scalability and zero-shot capability. To address this issue, we propose a scalable pipeline for automatic triplet generation, along with a fully synthetic dataset named Composed Image Retrieval on High-quality Synthetic Triplets (CIRHS). Our pipeline leverages a large language model (LLM) to generate diverse prompts, controlling a text-to-image generative model to produce image pairs with identical elements in each pair, which are then filtered and reorganized to form the CIRHS dataset. In addition, we introduce Hybrid Contextual Alignment (CoAlign), a novel CIR framework, which can accomplish global alignment and local reasoning within a broader context, enabling the model to learn more robust and informative representations. By utilizing the synthetic CIRHS dataset, CoAlign achieves outstanding zero-shot performance on three commonly used benchmarks, demonstrating for the first time the feasibility of training CIR models on a fully synthetic dataset. Furthermore, under supervised training, our method outperforms all the state-of-the-art supervised CIR approaches, validating the effectiveness of our proposed retrieval framework. The code and the CIRHS dataset will be released soon.
Authors: Xin Wu, Fei Teng, Yue Feng, Kaibo Shi, Zhuosheng Lin, Ji Zhang, James Wang
Abstract: Partial multi-label learning aims to extract knowledge from incompletely annotated data, which includes known correct labels, known incorrect labels, and unknown labels. The core challenge lies in accurately identifying the ambiguous relationships between labels and instances. In this paper, we emphasize that matching co-occurrence patterns between labels and instances is key to addressing this challenge. To this end, we propose Semantic Co-occurrence Insight Network (SCINet), a novel and effective framework for partial multi-label learning. Specifically, SCINet introduces a bi-dominant prompter module, which leverages an off-the-shelf multimodal model to capture text-image correlations and enhance semantic alignment. To reinforce instance-label interdependencies, we develop a cross-modality fusion module that jointly models inter-label correlations, inter-instance relationships, and co-occurrence patterns across instance-label assignments. Moreover, we propose an intrinsic semantic augmentation strategy that enhances the model's understanding of intrinsic data semantics by applying diverse image transformations, thereby fostering a synergistic relationship between label confidence and sample difficulty. Extensive experiments on four widely-used benchmark datasets demonstrate that SCINet surpasses state-of-the-art methods.
Authors: Haroon Wahab, Hassan Ugail, Lujain Jaleel
Abstract: Machine learning-based Deepfake detection models have achieved impressive results on benchmark datasets, yet their performance often deteriorates significantly when evaluated on out-of-distribution data. In this work, we investigate an ensemble-based approach for improving the generalization of deepfake detection systems across diverse datasets. Building on a recent open-source benchmark, we combine prediction probabilities from several state-of-the-art asymmetric models proposed at top venues. Our experiments span two distinct out-of-domain datasets and demonstrate that no single model consistently outperforms others across settings. In contrast, ensemble-based predictions provide more stable and reliable performance in all scenarios. Our results suggest that asymmetric ensembling offers a robust and scalable solution for real-world deepfake detection where prior knowledge of forgery type or quality is often unavailable.
Authors: Xinyu Wang, Muhammad Ibrahim, Haitian Wang, Atif Mansoor, Ajmal Mian
Abstract: Accurate geo-registration of LiDAR point clouds presents significant challenges in GNSS signal denied urban areas with high-rise buildings and bridges. Existing methods typically rely on real-time GNSS and IMU data, that require pre-calibration and assume stable positioning during data collection. However, this assumption often fails in dense urban areas, resulting in localization errors. To address this, we propose a structured geo-registration and spatial correction method that aligns 3D point clouds with satellite images, enabling frame-wise recovery of GNSS information and reconstruction of city scale 3D maps without relying on prior localization. The proposed approach employs a pre-trained Point Transformer model to segment the road points and then extracts the road skeleton and intersection points from the point cloud as well as the target map for alignment. Global rigid alignment of the two is performed using the intersection points, followed by local refinement using radial basis function (RBF) interpolation. Elevation correction is then applied to the point cloud based on terrain information from SRTM dataset to resolve vertical discrepancies. The proposed method was tested on the popular KITTI benchmark and a locally collected Perth (Western Australia) CBD dataset. On the KITTI dataset, our method achieved an average planimetric alignment standard deviation (STD) of 0.84~m across sequences with intersections, representing a 55.3\% improvement over the original dataset. On the Perth dataset, which lacks GNSS information, our method achieved an average STD of 0.96~m compared to the GPS data extracted from Google Maps API. This corresponds to a 77.4\% improvement from the initial alignment. Our method also resulted in elevation correlation gains of 30.5\% on the KITTI dataset and 50.4\% on the Perth dataset.
Authors: Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Osama Ahmed Khan, Shahid Munir Shah, Umema Mujeeb, Maheen Ali
Abstract: The modern text-to-image diffusion models boom has opened a new era in digital content production as it has proven the previously unseen ability to produce photorealistic and stylistically diverse imagery based on the semantics of natural-language descriptions. However, the consistent disadvantage of these models is that they cannot generate readable, meaningful, and correctly spelled text in generated images, which significantly limits the use of practical purposes like advertising, learning, and creative design. This paper introduces a new framework, namely Glyph-Conditioned Diffusion with Character-Aware Attention (GCDA), using which a typical diffusion backbone is extended by three well-designed modules. To begin with, the model has a dual-stream text encoder that encodes both semantic contextual information and explicit glyph representations, resulting in a character-aware representation of the input text that is rich in nature. Second, an attention mechanism that is aware of the character is proposed with a new attention segregation loss that aims to limit the attention distribution of each character independently in order to avoid distortion artifacts. Lastly, GCDA has an OCR-in-the-loop fine-tuning phase, where a full text perceptual loss, directly optimises models to be legible and accurately spell. Large scale experiments to benchmark datasets, such as MARIO-10M and T2I-CompBench, reveal that GCDA sets a new state-of-the-art on all metrics, with better character based metrics on text rendering (Character Error Rate: 0.08 vs 0.21 for the previous best; Word Error Rate: 0.15 vs 0.25), human perception, and comparable image synthesis quality on high-fidelity (FID: 14.3).
Authors: Alexandre Symeonidis-Herzig, \"Ozge Mercano\u{g}lu Sincan, Richard Bowden
Abstract: Realistic, high-fidelity 3D facial animations are crucial for expressive avatar systems in human-computer interaction and accessibility. Although prior methods show promising quality, their reliance on the mesh domain limits their ability to fully leverage the rapid visual innovations seen in 2D computer vision and graphics. We propose VisualSpeaker, a novel method that bridges this gap using photorealistic differentiable rendering, supervised by visual speech recognition, for improved 3D facial animation. Our contribution is a perceptual lip-reading loss, derived by passing photorealistic 3D Gaussian Splatting avatar renders through a pre-trained Visual Automatic Speech Recognition model during training. Evaluation on the MEAD dataset demonstrates that VisualSpeaker improves both the standard Lip Vertex Error metric by 56.1% and the perceptual quality of the generated animations, while retaining the controllability of mesh-driven animation. This perceptual focus naturally supports accurate mouthings, essential cues that disambiguate similar manual signs in sign language avatars.
Authors: Chang Liu, Ye Pan, Chenyang Ding, Susanto Rahardja, Xiaokang Yang
Abstract: Audio-driven emotional 3D facial animation aims to generate synchronized lip movements and vivid facial expressions. However, most existing approaches focus on static and predefined emotion labels, limiting their diversity and naturalness. To address these challenges, we propose MEDTalk, a novel framework for fine-grained and dynamic emotional talking head generation. Our approach first disentangles content and emotion embedding spaces from motion sequences using a carefully designed cross-reconstruction process, enabling independent control over lip movements and facial expressions. Beyond conventional audio-driven lip synchronization, we integrate audio and speech text, predicting frame-wise intensity variations and dynamically adjusting static emotion features to generate realistic emotional expressions. Furthermore, to enhance control and personalization, we incorporate multimodal inputs-including text descriptions and reference expression images-to guide the generation of user-specified facial expressions. With MetaHuman as the priority, our generated results can be conveniently integrated into the industrial production pipeline.
Authors: Tongtong Cheng, Rongzhen Li, Yixin Xiong, Tao Zhang, Jing Wang, Kai Liu
Abstract: Accurate driving behavior recognition and reasoning are critical for autonomous driving video understanding. However, existing methods often tend to dig out the shallow causal, fail to address spurious correlations across modalities, and ignore the ego-vehicle level causality modeling. To overcome these limitations, we propose a novel Multimodal Causal Analysis Model (MCAM) that constructs latent causal structures between visual and language modalities. Firstly, we design a multi-level feature extractor to capture long-range dependencies. Secondly, we design a causal analysis module that dynamically models driving scenarios using a directed acyclic graph (DAG) of driving states. Thirdly, we utilize a vision-language transformer to align critical visual features with their corresponding linguistic expressions. Extensive experiments on the BDD-X, and CoVLA datasets demonstrate that MCAM achieves SOTA performance in visual-language causal relationship learning. Furthermore, the model exhibits superior capability in capturing causal characteristics within video sequences, showcasing its effectiveness for autonomous driving applications. The code is available at https://github.com/SixCorePeach/MCAM.
Authors: Francesco Milano, Manuel L\'opez-Antequera, Naina Dhingra, Roland Siegwart, Robert Thiel
Abstract: Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-shading and photometric stereo. The vast majority of existing approaches for normal integration handle only implicitly the presence of depth discontinuities and are limited to orthographic or ideal pinhole cameras. In this paper, we propose a novel formulation that allows modeling discontinuities explicitly and handling generic central cameras. Our key idea is based on a local planarity assumption, that we model through constraints between surface normals and ray directions. Compared to existing methods, our approach more accurately approximates the relation between depth and surface normals, achieves state-of-the-art results on the standard normal integration benchmark, and is the first to directly handle generic central camera models.
Authors: Chihan Huang, Hao Tang
Abstract: Despite the success of deep learning across various domains, it remains vulnerable to adversarial attacks. Although many existing adversarial attack methods achieve high success rates, they typically rely on $\ell_{p}$-norm perturbation constraints, which do not align with human perceptual capabilities. Consequently, researchers have shifted their focus toward generating natural, unrestricted adversarial examples (UAEs). GAN-based approaches suffer from inherent limitations, such as poor image quality due to instability and mode collapse. Meanwhile, diffusion models have been employed for UAE generation, but they still rely on iterative PGD perturbation injection, without fully leveraging their central denoising capabilities. In this paper, we introduce a novel approach for generating UAEs based on diffusion models, named ScoreAdv. This method incorporates an interpretable adversarial guidance mechanism to gradually shift the sampling distribution towards the adversarial distribution, while using an interpretable saliency map to inject the visual information of a reference image into the generated samples. Notably, our method is capable of generating an unlimited number of natural adversarial examples and can attack not only classification models but also retrieval models. We conduct extensive experiments on ImageNet and CelebA datasets, validating the performance of ScoreAdv across ten target models in both black-box and white-box settings. Our results demonstrate that ScoreAdv achieves state-of-the-art attack success rates and image quality. Furthermore, the dynamic balance between denoising and adversarial perturbation enables ScoreAdv to remain robust even under defensive measures.
Authors: Joaquim Comas, Alexander Joel Vera, Xavier Vives, Eleonora De Filippi, Alexandre Pereda, Federico Sukno
Abstract: In recent years, affective computing and its applications have become a fast-growing research topic. Despite significant advancements, the lack of affective multi-modal datasets remains a major bottleneck in developing accurate emotion recognition systems. Furthermore, the use of contact-based devices during emotion elicitation often unintentionally influences the emotional experience, reducing or altering the genuine spontaneous emotional response. This limitation highlights the need for methods capable of extracting affective cues from multiple modalities without physical contact, such as remote physiological emotion recognition. To address this, we present the Contactless Affective States Through Physiological Signals Database (CAST-Phys), a novel high-quality dataset explicitly designed for multi-modal remote physiological emotion recognition using facial and physiological cues. The dataset includes diverse physiological signals, such as photoplethysmography (PPG), electrodermal activity (EDA), and respiration rate (RR), alongside high-resolution uncompressed facial video recordings, enabling the potential for remote signal recovery. Our analysis highlights the crucial role of physiological signals in realistic scenarios where facial expressions alone may not provide sufficient emotional information. Furthermore, we demonstrate the potential of remote multi-modal emotion recognition by evaluating the impact of individual and fused modalities, showcasing its effectiveness in advancing contactless emotion recognition technologies.
Authors: Murilo Gustineli, Anthony Miyaguchi, Adrian Cheung, Divyansh Khattak
Abstract: We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images. Our pipeline combines (i) a fine-tuned Vision Transformer ViTD2PC24All for patch-level inference, (ii) a 4x4 tiling strategy that aligns patch size with the network's 518x518 receptive field, and (iii) domain-prior adaptation through PaCMAP + K-Means visual clustering and geolocation filtering. Tile predictions are aggregated by majority vote and re-weighted with cluster-specific Bayesian priors, yielding a macro-averaged F1 of 0.348 (private leaderboard) while requiring no additional training. All code, configuration files, and reproducibility scripts are publicly available at https://github.com/dsgt-arc/plantclef-2025.
Authors: Jiayi Song, Zihan Ye, Qingyuan Zhou, Weidong Yang, Ben Fei, Jingyi Xu, Ying He, Wanli Ouyang
Abstract: Accurately rendering scenes with reflective surfaces remains a significant challenge in novel view synthesis, as existing methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) often misinterpret reflections as physical geometry, resulting in degraded reconstructions. Previous methods rely on incomplete and non-generalizable geometric constraints, leading to misalignment between the positions of Gaussian splats and the actual scene geometry. When dealing with real-world scenes containing complex geometry, the accumulation of Gaussians further exacerbates surface artifacts and results in blurred reconstructions. To address these limitations, in this work, we propose Ref-Unlock, a novel geometry-aware reflection modeling framework based on 3D Gaussian Splatting, which explicitly disentangles transmitted and reflected components to better capture complex reflections and enhance geometric consistency in real-world scenes. Our approach employs a dual-branch representation with high-order spherical harmonics to capture high-frequency reflective details, alongside a reflection removal module providing pseudo reflection-free supervision to guide clean decomposition. Additionally, we incorporate pseudo-depth maps and a geometry-aware bilateral smoothness constraint to enhance 3D geometric consistency and stability in decomposition. Extensive experiments demonstrate that Ref-Unlock significantly outperforms classical GS-based reflection methods and achieves competitive results with NeRF-based models, while enabling flexible vision foundation models (VFMs) driven reflection editing. Our method thus offers an efficient and generalizable solution for realistic rendering of reflective scenes. Our code is available at https://ref-unlock.github.io/.
Authors: Zhiyu Tan, Hao Yang, Luozheng Qin, Jia Gong, Mengping Yang, Hao Li
Abstract: Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images, creating a gap in the development of unified models for video understanding and generation. This report presents Omni-Video, an efficient and effective unified framework for video understanding, generation, as well as instruction-based editing. Our key insight is to teach existing multimodal large language models (MLLMs) to produce continuous visual clues that are used as the input of diffusion decoders, which produce high-quality videos conditioned on these visual clues. To fully unlock the potential of our system for unified video modeling, we integrate several technical improvements: 1) a lightweight architectural design that respectively attaches a vision head on the top of MLLMs and a adapter before the input of diffusion decoders, the former produce visual tokens for the latter, which adapts these visual tokens to the conditional space of diffusion decoders; and 2) an efficient multi-stage training scheme that facilitates a fast connection between MLLMs and diffusion decoders with limited data and computational resources. We empirically demonstrate that our model exhibits satisfactory generalization abilities across video generation, editing and understanding tasks.
Authors: Haoyu Wang, Lei Zhang, Wei Wei, Chen Ding, Yanning Zhang
Abstract: Diffusion models has underpinned much recent advances of dataset augmentation in various computer vision tasks. However, when involving generating multi-object images as real scenarios, most existing methods either rely entirely on text condition, resulting in a deviation between the generated objects and the original data, or rely too much on the original images, resulting in a lack of diversity in the generated images, which is of limited help to downstream tasks. To mitigate both problems with one stone, we propose a prompt-free conditional diffusion framework for multi-object image augmentation. Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text, and inject knowledge into the diffusion model through LoRA to alleviate the category deviation between the original model and the target dataset. In addition, we design a reward model based counting loss to assist the traditional reconstruction loss for model training. By constraining the object counts of each category instead of pixel-by-pixel constraints, bridging the quantity deviation between the generated data and the original data while improving the diversity of the generated data. Experimental results demonstrate the superiority of the proposed method over several representative state-of-the-art baselines and showcase strong downstream task gain and out-of-domain generalization capabilities. Code is available at \href{https://github.com/00why00/PFCD}{here}.
Authors: Mustafa Bayram G\"ucen
Abstract: In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of two convolutional layers, max pooling, and fully connected layers was implemented. SoftReMish was evaluated against popular activation functions including ReLU, Tanh, and Mish by replacing the activation function in all trainable layers. The model performance was assessed in terms of minimum training loss and maximum validation accuracy. Results showed that SoftReMish achieved a minimum loss (3.14e-8) and a validation accuracy (99.41%), outperforming all other functions tested. These findings demonstrate that SoftReMish offers better convergence behavior and generalization capability, making it a promising candidate for visual recognition tasks.
Authors: Nathan Kessler, Robin Magnet, Jean Feydy
Abstract: Smoothing a signal based on local neighborhoods is a core operation in machine learning and geometry processing. On well-structured domains such as vector spaces and manifolds, the Laplace operator derived from differential geometry offers a principled approach to smoothing via heat diffusion, with strong theoretical guarantees. However, constructing such Laplacians requires a carefully defined domain structure, which is not always available. Most practitioners thus rely on simple convolution kernels and message-passing layers, which are biased against the boundaries of the domain. We bridge this gap by introducing a broad class of smoothing operators, derived from general similarity or adjacency matrices, and demonstrate that they can be normalized into diffusion-like operators that inherit desirable properties from Laplacians. Our approach relies on a symmetric variant of the Sinkhorn algorithm, which rescales positive smoothing operators to match the structural behavior of heat diffusion. This construction enables Laplacian-like smoothing and processing of irregular data such as point clouds, sparse voxel grids or mixture of Gaussians. We show that the resulting operators not only approximate heat diffusion but also retain spectral information from the Laplacian itself, with applications to shape analysis and matching.
Authors: Yunhan Yang, Yufan Zhou, Yuan-Chen Guo, Zi-Xin Zou, Yukun Huang, Ying-Tian Liu, Hao Xu, Ding Liang, Yan-Pei Cao, Xihui Liu
Abstract: The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content.
Authors: Prahitha Movva, Naga Harshita Marupaka
Abstract: Technical reports and articles often contain valuable information in the form of semi-structured data like charts, and figures. Interpreting these and using the information from them is essential for downstream tasks such as question answering (QA). Current approaches to visual question answering often struggle with the precision required for scientific data interpretation, particularly in handling numerical values, multi-step reasoning over visual elements, and maintaining consistency between visual observation and textual reasoning. We present our approach to the SciVQA 2025 shared task, focusing on answering visual and non-visual questions grounded in scientific figures from scholarly articles. We conducted a series of experiments using models with 5B to 8B parameters. Our strongest individual model, InternVL3, achieved ROUGE-1 and ROUGE-L F1 scores of \textbf{0.740} and a BERTScore of \textbf{0.983} on the SciVQA test split. We also developed an ensemble model with multiple vision language models (VLMs). Through error analysis on the validation split, our ensemble approach improved performance compared to most individual models, though InternVL3 remained the strongest standalone performer. Our findings underscore the effectiveness of prompt optimization, chain-of-thought reasoning and ensemble modeling in improving the model's ability in visual question answering.
Authors: Yuchen Huang, Zhiyuan Fan, Zhitao He, Sandeep Polisetty, Wenyan Li, Yi R. Fung
Abstract: Pretrained vision-language models (VLMs) such as CLIP excel in multimodal understanding but struggle with contextually relevant fine-grained visual features, making it difficult to distinguish visually similar yet culturally distinct concepts. This limitation stems from the scarcity of high-quality culture-specific datasets, the lack of integrated contextual knowledge, and the absence of hard negatives highlighting subtle distinctions. To address these challenges, we first design a data curation pipeline that leverages open-sourced VLMs and text-to-image diffusion models to construct CulTwin, a synthetic cultural dataset. This dataset consists of paired concept-caption-image triplets, where concepts visually resemble each other but represent different cultural contexts. Then, we fine-tune CLIP on CulTwin to create CultureCLIP, which aligns cultural concepts with contextually enhanced captions and synthetic images through customized contrastive learning, enabling finer cultural differentiation while preserving generalization capabilities. Experiments on culturally relevant benchmarks show that CultureCLIP outperforms the base CLIP, achieving up to a notable 5.49% improvement in fine-grained concept recognition on certain tasks, while preserving CLIP's original generalization ability, validating the effectiveness of our data synthesis and VLM backbone training paradigm in capturing subtle cultural distinctions.
Authors: Aleksandar Jevti\'c, Christoph Reich, Felix Wimbauer, Oliver Hahn, Christian Rupprecht, Stefan Roth, Daniel Cremers
Abstract: Semantic scene completion (SSC) aims to infer both the 3D geometry and semantics of a scene from single images. In contrast to prior work on SSC that heavily relies on expensive ground-truth annotations, we approach SSC in an unsupervised setting. Our novel method, SceneDINO, adapts techniques from self-supervised representation learning and 2D unsupervised scene understanding to SSC. Our training exclusively utilizes multi-view consistency self-supervision without any form of semantic or geometric ground truth. Given a single input image, SceneDINO infers the 3D geometry and expressive 3D DINO features in a feed-forward manner. Through a novel 3D feature distillation approach, we obtain unsupervised 3D semantics. In both 3D and 2D unsupervised scene understanding, SceneDINO reaches state-of-the-art segmentation accuracy. Linear probing our 3D features matches the segmentation accuracy of a current supervised SSC approach. Additionally, we showcase the domain generalization and multi-view consistency of SceneDINO, taking the first steps towards a strong foundation for single image 3D scene understanding.
Authors: Keyan Chen, Chenyang Liu, Bowen Chen, Jiafan Zhang, Zhengxia Zou, Zhenwei Shi
Abstract: Referring Remote Sensing Image Segmentation provides a flexible and fine-grained framework for remote sensing scene analysis via vision-language collaborative interpretation. Current approaches predominantly utilize a three-stage pipeline encompassing dual-modal encoding, cross-modal interaction, and pixel decoding. These methods demonstrate significant limitations in managing complex semantic relationships and achieving precise cross-modal alignment, largely due to their coupled processing mechanism that conflates target localization with boundary delineation. This architectural coupling amplifies error propagation under semantic ambiguity while restricting model generalizability and interpretability. To address these issues, we propose RSRefSeg 2, a decoupling paradigm that reformulates the conventional workflow into a collaborative dual-stage framework: coarse localization followed by fine segmentation. RSRefSeg 2 integrates CLIP's cross-modal alignment strength with SAM's segmentation generalizability through strategic foundation model collaboration. Specifically, CLIP is employed as the dual-modal encoder to activate target features within its pre-aligned semantic space and generate localization prompts. To mitigate CLIP's misactivation challenges in multi-entity scenarios described by referring texts, a cascaded second-order prompter is devised, which enhances precision through implicit reasoning via decomposition of text embeddings into complementary semantic subspaces. These optimized semantic prompts subsequently direct the SAM to generate pixel-level refined masks, thereby completing the semantic transmission pipeline. Extensive experiments (RefSegRS, RRSIS-D, and RISBench) demonstrate that RSRefSeg 2 surpasses contemporary methods in segmentation accuracy (+~3% gIoU) and complex semantic interpretation. Code is available at: https://github.com/KyanChen/RSRefSeg2.
Authors: In\`es Hyeonsu Kim, Seokju Cho, Jahyeok Koo, Junghyun Park, Jiahui Huang, Joon-Young Lee, Seungryong Kim
Abstract: Human motion, with its inherent complexities, such as non-rigid deformations, articulated movements, clothing distortions, and frequent occlusions caused by limbs or other individuals, provides a rich and challenging source of supervision that is crucial for training robust and generalizable point trackers. Despite the suitability of human motion, acquiring extensive training data for point tracking remains difficult due to laborious manual annotation. Our proposed pipeline, AnthroTAP, addresses this by proposing an automated pipeline to generate pseudo-labeled training data, leveraging the Skinned Multi-Person Linear (SMPL) model. We first fit the SMPL model to detected humans in video frames, project the resulting 3D mesh vertices onto 2D image planes to generate pseudo-trajectories, handle occlusions using ray-casting, and filter out unreliable tracks based on optical flow consistency. A point tracking model trained on AnthroTAP annotated dataset achieves state-of-the-art performance on the TAP-Vid benchmark, surpassing other models trained on real videos while using 10,000 times less data and only 1 day in 4 GPUs, compared to 256 GPUs used in recent state-of-the-art.
Authors: Xiaoyuan Li, Xinru Xue, Bohan Zhang, Ye Sun, Shoushuo Xi, Gang Liu
Abstract: Brain-computer interface (BCI) based on motor imagery (MI) enables direct control of external devices by decoding the electroencephalogram (EEG) generated in the brain during imagined movements. However, due to inter-individual variability in brain activity, existing BCI models exhibit poor adaptability across subjects, thereby limiting their generalizability and widespread application. To address this issue, this paper proposes a cross-subject BCI algorithm named Cross-Subject DD (CSDD), which constructs a universal BCI model by extracting common features across subjects. The specific methods include: 1) training personalized models for each subject; 2) transforming personalized models into relation spectrums; 3) identifying common features through statistical analysis; and 4) constructing a cross-subject universal model based on common features. The experiments utilized the BCIC IV 2a dataset, involving nine subjects. Eight of these subjects were selected for training and extracing the common features, and the cross-subject decoding performance of the model was validated on the remaining subject. The results demonstrate that, compared with existing similar methods, our approach achieves a 3.28% improvement in performance. This paper introduces for the first time a novel method for extracting pure common features and constructing a universal cross-subject BCI model, thereby facilitating broader applications of BCI technology.
Authors: Saqib Nazir (UNICAEN), Olivier L\'ezoray (UNICAEN), S\'ebastien Bougleux (UNICAEN)
Abstract: 3D meshes are fundamental data representations for capturing complex geometric shapes in computer vision and graphics applications. While Convolutional Neural Networks (CNNs) have excelled in structured data like images, extending them to irregular 3D meshes is challenging due to the non-Euclidean nature of the data. Graph Convolutional Networks (GCNs) offer a solution by applying convolutions to graph-structured data, but many existing methods rely on isotropic filters or spectral decomposition, limiting their ability to capture both local and global mesh features. In this paper, we introduce 3D Geometric Mesh Network (3DGeoMeshNet), a novel GCN-based framework that uses anisotropic convolution layers to effectively learn both global and local features directly in the spatial domain. Unlike previous approaches that convert meshes into intermediate representations like voxel grids or point clouds, our method preserves the original polygonal mesh format throughout the reconstruction process, enabling more accurate shape reconstruction. Our architecture features a multi-scale encoder-decoder structure, where separate global and local pathways capture both large-scale geometric structures and fine-grained local details. Extensive experiments on the COMA dataset containing human faces demonstrate the efficiency of 3DGeoMeshNet in terms of reconstruction accuracy.
Authors: Daniel Cie\'slak, Miriam Reca, Olena Onyshchenko, Jacek Rumi\'nski
Abstract: Accurate segmentation of wounds and scale markers in clinical images remainsa significant challenge, crucial for effective wound management and automatedassessment. In this study, we propose a novel dual-attention U-Net++ archi-tecture, integrating channel-wise (SCSE) and spatial attention mechanisms toaddress severe class imbalance and variability in medical images effectively.Initially, extensive benchmarking across diverse architectures and encoders via 5-fold cross-validation identified EfficientNet-B7 as the optimal encoder backbone.Subsequently, we independently trained two class-specific models with tailoredpreprocessing, extensive data augmentation, and Bayesian hyperparameter tun-ing (WandB sweeps). The final model ensemble utilized Test Time Augmentationto further enhance prediction reliability. Our approach was evaluated on a bench-mark dataset from the NBC 2025 & PCBBE 2025 competition. Segmentationperformance was quantified using a weighted F1-score (75% wounds, 25% scalemarkers), calculated externally by competition organizers on undisclosed hard-ware. The proposed approach achieved an F1-score of 0.8640, underscoring itseffectiveness for complex medical segmentation tasks.
Authors: Madina Kojanazarova, Florentin Bieder, Robin Sandk\"uhler, Philippe C. Cattin
Abstract: Soft tissue simulation in virtual environments is becoming increasingly important for medical applications. However, the high deformability of soft tissue poses significant challenges. Existing methods rely on segmentation, meshing and estimation of stiffness properties of tissues. In addition, the integration of haptic feedback requires precise force estimation to enable a more immersive experience. We introduce a novel data-driven model, a conditional graph neural network (cGNN) to tackle this complexity. Our model takes surface points and the location of applied forces, and is specifically designed to predict the deformation of the points and the forces exerted on them. We trained our model on experimentally collected surface tracking data of a soft tissue phantom and used transfer learning to overcome the data scarcity by initially training it with mass-spring simulations and fine-tuning it with the experimental data. This approach improves the generalisation capability of the model and enables accurate predictions of tissue deformations and corresponding interaction forces. The results demonstrate that the model can predict deformations with a distance error of 0.35$\pm$0.03 mm for deformations up to 30 mm and the force with an absolute error of 0.37$\pm$0.05 N for forces up to 7.5 N. Our data-driven approach presents a promising solution to the intricate challenge of simulating soft tissues within virtual environments. Beyond its applicability in medical simulations, this approach holds the potential to benefit various fields where realistic soft tissue simulations are required.
Authors: Yi Liu, Yiyang Wen, Zekun Zhou, Junqi Ma, Linghang Wang, Yucheng Yao, Liu Shi, Qiegen Liu
Abstract: Generative diffusion models have received increasing attention in medical imaging, particularly in limited-angle computed tomography (LACT). Standard diffusion models achieve high-quality image reconstruction but require a large number of sampling steps during inference, resulting in substantial computational overhead. Although skip-sampling strategies have been proposed to improve efficiency, they often lead to loss of fine structural details. To address this issue, we propose a prior information embedding and wavelet feature fusion fast sampling diffusion model for LACT reconstruction. The PWD enables efficient sampling while preserving reconstruction fidelity in LACT, and effectively mitigates the degradation typically introduced by skip-sampling. Specifically, during the training phase, PWD maps the distribution of LACT images to that of fully sampled target images, enabling the model to learn structural correspondences between them. During inference, the LACT image serves as an explicit prior to guide the sampling trajectory, allowing for high-quality reconstruction with significantly fewer steps. In addition, PWD performs multi-scale feature fusion in the wavelet domain, effectively enhancing the reconstruction of fine details by leveraging both low-frequency and high-frequency information. Quantitative and qualitative evaluations on clinical dental arch CBCT and periapical datasets demonstrate that PWD outperforms existing methods under the same sampling condition. Using only 50 sampling steps, PWD achieves at least 1.7 dB improvement in PSNR and 10% gain in SSIM.
Authors: Aiur Nanzatov, Lourdes Pe\~na-Castillo, Oscar Meruvia-Pastor
Abstract: Two-factor authentication (2FA) has become widely adopted as an efficient and secure way to validate someone's identity online. Two-factor authentication is difficult in virtual reality (VR) because users are usually wearing a head-mounted display (HMD) which does not allow them to see their real-world surroundings. We present NRXR-ID, a technique to implement two-factor authentication while using extended reality systems and smartphones. The proposed method allows users to complete an authentication challenge using their smartphones without removing their HMD. We performed a user study where we explored four types of challenges for users, including a novel checkers-style challenge. Users responded to these challenges under three different configurations, including a technique that uses the smartphone to support gaze-based selection without the use of VR controllers. A 4X3 within-subjects design allowed us to study all the variations proposed. We collected performance metrics and performed user experience questionnaires to collect subjective impressions from 30 participants. Results suggest that the checkers-style visual matching challenge was the most appropriate option, followed by entering a digital PIN challenge submitted via the smartphone and answered within the VR environment.
Authors: Lijie Huang, Jingyi Yin, Jingke Zhang, U-Wai Lok, Ryan M. DeRuiter, Jieyang Jin, Kate M. Knoll, Kendra E. Petersen, James D. Krier, Xiang-yang Zhu, Gina K. Hesley, Kathryn A. Robinson, Andrew J. Bentall, Thomas D. Atwell, Andrew D. Rule, Lilach O. Lerman, Shigao Chen, Chengwu Huang
Abstract: Ultrasound microvascular imaging (UMI) is often hindered by low signal-to-noise ratio (SNR), especially in contrast-free or deep tissue scenarios, which impairs subsequent vascular quantification and reliable disease diagnosis. To address this challenge, we propose Half-Angle-to-Half-Angle (HA2HA), a self-supervised denoising framework specifically designed for UMI. HA2HA constructs training pairs from complementary angular subsets of beamformed radio-frequency (RF) blood flow data, across which vascular signals remain consistent while noise varies. HA2HA was trained using in-vivo contrast-free pig kidney data and validated across diverse datasets, including contrast-free and contrast-enhanced data from pig kidneys, as well as human liver and kidney. An improvement exceeding 15 dB in both contrast-to-noise ratio (CNR) and SNR was observed, indicating a substantial enhancement in image quality. In addition to power Doppler imaging, denoising directly in the RF domain is also beneficial for other downstream processing such as color Doppler imaging (CDI). CDI results of human liver derived from the HA2HA-denoised signals exhibited improved microvascular flow visualization, with a suppressed noisy background. HA2HA offers a label-free, generalizable, and clinically applicable solution for robust vascular imaging in both contrast-free and contrast-enhanced UMI.
Authors: Haochen Huang, Jiahuan Pei, Mohammad Aliannejadi, Xin Sun, Moonisa Ahsan, Pablo Cesar, Chuang Yu, Zhaochun Ren, Junxiao Wang
Abstract: Vision-language models (VLMs) are essential for enabling AI-powered smart assistants to interpret and reason in multimodal environments. However, their application in augmented reality (AR) training remains largely unexplored. In this work, we introduce a comprehensive dataset tailored for AR training, featuring systematized vision-language tasks, and evaluate nine state-of-the-art VLMs on it. Our results reveal that even advanced models, including GPT-4o, struggle with fine-grained assembly tasks, achieving a maximum F1 score of just 40.54% on state detection. These findings highlight the demand for enhanced datasets, benchmarks, and further research to improve fine-grained vision-language alignment. Beyond technical contributions, our work has broader social implications, particularly in empowering blind and visually impaired users with equitable access to AI-driven learning opportunities. We provide all related resources, including the dataset, source code, and evaluation results, to support the research community.
Authors: Pedro R. A. S. Bassi, Wenxuan Li, Jieneng Chen, Zheren Zhu, Tianyu Lin, Sergio Decherchi, Andrea Cavalli, Kang Wang, Yang Yang, Alan L. Yuille, Zongwei Zhou
Abstract: Tumor segmentation in CT scans is key for diagnosis, surgery, and prognosis, yet segmentation masks are scarce because their creation requires time and expertise. Public abdominal CT datasets have from dozens to a couple thousand tumor masks, but hospitals have hundreds of thousands of tumor CTs with radiology reports. Thus, leveraging reports to improve segmentation is key for scaling. In this paper, we propose a report-supervision loss (R-Super) that converts radiology reports into voxel-wise supervision for tumor segmentation AI. We created a dataset with 6,718 CT-Report pairs (from the UCSF Hospital), and merged it with public CT-Mask datasets (from AbdomenAtlas 2.0). We used our R-Super to train with these masks and reports, and strongly improved tumor segmentation in internal and external validation--F1 Score increased by up to 16% with respect to training with masks only. By leveraging readily available radiology reports to supplement scarce segmentation masks, R-Super strongly improves AI performance both when very few training masks are available (e.g., 50), and when many masks were available (e.g., 1.7K). Project: https://github.com/MrGiovanni/R-Super
Authors: Young Hun Kim, Seungyeon Kim, Yonghyeon Lee, Frank Chongwoo Park
Abstract: Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world settings where full-view or reliable depth data are often unavailable. Existing methods, whether based on strong symmetry priors or supervised learning on curated datasets, fail to generalize to such scenarios. In this work, we introduce DreamGrasp, a framework that leverages the imagination capability of large-scale pre-trained image generative models to infer the unobserved parts of a scene. By combining coarse 3D reconstruction, instance segmentation via contrastive learning, and text-guided instance-wise refinement, DreamGrasp circumvents limitations of prior methods and enables robust 3D reconstruction in complex, multi-object environments. Our experiments show that DreamGrasp not only recovers accurate object geometry but also supports downstream tasks like sequential decluttering and target retrieval with high success rates.
Authors: Jiaqi Guo, Santiago L\'opez-Tapia
Abstract: Limited-Angle Computed Tomography (LACT) is a challenging inverse problem where missing angular projections lead to incomplete sinograms and severe artifacts in the reconstructed images. While recent learning-based methods have demonstrated effectiveness, most of them assume ideal, noise-free measurements and fail to address the impact of measurement noise. To overcome this limitation, we treat LACT as a sinogram inpainting task and propose a diffusion-based framework that completes missing angular views using a Mean-Reverting Stochastic Differential Equation (MR-SDE) formulation. To improve robustness under realistic noise, we propose RNSD$^+$, a novel noise-aware rectification mechanism that explicitly models inference-time uncertainty, enabling reliable and robust reconstruction. Extensive experiments demonstrate that our method consistently surpasses baseline models in data consistency and perceptual quality, and generalizes well across varying noise intensity and acquisition scenarios.
Authors: Zhiyuan Yang, Kai Li, Sophia Ghamoshi Ramandi, Patricia Brassard, Hakim Khellaf, Vincent Quoc-Huy Trinh, Jennifer Zhang, Lina Chen, Corwyn Rowsell, Sonal Varma, Kostas Plataniotis, Mahdi S. Hosseini
Abstract: Computational pathology (CoPath) leverages histopathology images to enhance diagnostic precision and reproducibility in clinical pathology. However, publicly available datasets for CoPath that are annotated with extensive histological tissue type (HTT) taxonomies at a granular level remain scarce due to the significant expertise and high annotation costs required. Existing datasets, such as the Atlas of Digital Pathology (ADP), address this by offering diverse HTT annotations generalized to multiple organs, but limit the capability for in-depth studies on specific organ diseases. Building upon this foundation, we introduce ADPv2, a novel dataset focused on gastrointestinal histopathology. Our dataset comprises 20,004 image patches derived from healthy colon biopsy slides, annotated according to a hierarchical taxonomy of 32 distinct HTTs of 3 levels. Furthermore, we train a multilabel representation learning model following a two-stage training procedure on our ADPv2 dataset. We leverage the VMamba architecture and achieving a mean average precision (mAP) of 0.88 in multilabel classification of colon HTTs. Finally, we show that our dataset is capable of an organ-specific in-depth study for potential biomarker discovery by analyzing the model's prediction behavior on tissues affected by different colon diseases, which reveals statistical patterns that confirm the two pathological pathways of colon cancer development. Our dataset is publicly available at https://zenodo.org/records/15307021
Authors: Haitao Lu, Haijier Chen, Haoze Liu, Shoujian Zhang, Bo Xu, Ziao Liu
Abstract: In autonomous robotic systems, precise localization is a prerequisite for safe navigation. However, in complex urban environments, GNSS positioning often suffers from signal occlusion and multipath effects, leading to unreliable absolute positioning. Traditional mapping approaches are constrained by storage requirements and computational inefficiency, limiting their applicability to resource-constrained robotic platforms. To address these challenges, we propose 3DGS-LSR: a large-scale relocalization framework leveraging 3D Gaussian Splatting (3DGS), enabling centimeter-level positioning using only a single monocular RGB image on the client side. We combine multi-sensor data to construct high-accuracy 3DGS maps in large outdoor scenes, while the robot-side localization requires just a standard camera input. Using SuperPoint and SuperGlue for feature extraction and matching, our core innovation is an iterative optimization strategy that refines localization results through step-by-step rendering, making it suitable for real-time autonomous navigation. Experimental validation on the KITTI dataset demonstrates our 3DGS-LSR achieves average positioning accuracies of 0.026m, 0.029m, and 0.081m in town roads, boulevard roads, and traffic-dense highways respectively, significantly outperforming other representative methods while requiring only monocular RGB input. This approach provides autonomous robots with reliable localization capabilities even in challenging urban environments where GNSS fails.
Authors: Till Nicke, Daniela Schacherer, Jan Raphael Sch\"afer, Natalia Artysh, Antje Prasse, Andr\'e Homeyer, Andrea Schenk, Henning H\"ofener, Johannes Lotz
Abstract: Foundation models (FMs) are transforming the field of computational pathology by offering new approaches to analyzing histopathology images. Typically relying on weeks of training on large databases, the creation of FMs is a resource-intensive process in many ways. In this paper, we introduce the extension of our supervised foundation model, Tissue Concepts, to whole slide images, called Tissue Concepts v2 (TCv2), a supervised foundation model for whole slide images to address the issue above. TCv2 uses supervised, end-to-end multitask learning on slide-level labels. Training TCv2 uses a fraction of the training resources compared to self-supervised training. The presented model shows superior performance compared to SSL-trained models in cancer subtyping benchmarks and is fully trained on freely available data. Furthermore, a shared trained attention module provides an additional layer of explainability across different tasks.
Authors: Sofiia Chorna, Kateryna Tarelkina, Elo\"ise Berthier, Gianni Franchi
Abstract: While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic interpretability. Our approach enables a global dissection of model behavior by analyzing how high-level semantic attributes (referred to as concepts) emerge, interact, and propagate through internal model components. Unlike prior work that isolates individual neurons or predictions, our framework systematically quantifies how semantic concepts are represented across layers, revealing latent circuits and information flow that underlie model decision-making. A key innovation is our visualization platform that we named BAGEL (for Bias Analysis with a Graph for global Explanation Layers), which presents these insights in a structured knowledge graph, allowing users to explore concept-class relationships, identify spurious correlations, and enhance model trustworthiness. Our framework is model-agnostic, scalable, and contributes to a deeper understanding of how deep learning models generalize (or fail to) in the presence of dataset biases. The demonstration is available at https://knowledge-graph-ui-4a7cb5.gitlab.io/.
Authors: Tangzheng Lian, Guanyu Hu, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan
Abstract: Domain generalization (DG) and algorithmic fairness are two critical challenges in machine learning. However, most DG methods focus only on minimizing expected risk in the unseen target domain without considering algorithmic fairness. Conversely, fairness methods typically do not account for domain shifts, so the fairness achieved during training may not generalize to unseen test domains. In this work, we bridge these gaps by studying the problem of Fair Domain Generalization (FairDG), which aims to minimize both expected risk and fairness violations in unseen target domains. We derive novel mutual information-based upper bounds for expected risk and fairness violations in multi-class classification tasks with multi-group sensitive attributes. These bounds provide key insights for algorithm design from an information-theoretic perspective. Guided by these insights, we introduce PAFDG (Pareto-Optimal Fairness for Domain Generalization), a practical framework that solves the FairDG problem and models the utility-fairness trade-off through Pareto optimization. Experiments on real-world vision and language datasets show that PAFDG achieves superior utility-fairness trade-offs compared to existing methods.
Authors: Xingwei He, Kit Mills Bransby, Ahmet Emir Ulutas, Thamil Kumaran, Nathan Angelo Lecaros Yap, Gonul Zeren, Hesong Zeng, Yaojun Zhang, Andreas Baumbach, James Moon, Anthony Mathur, Jouke Dijkstra, Qianni Zhang, Lorenz Raber, Christos V Bourantas
Abstract: Aims: To develop a deep-learning (DL) framework that will allow fully automated longitudinal and circumferential co-registration of intravascular ultrasound (IVUS) and optical coherence tomography (OCT) images. Methods and results: Data from 230 patients (714 vessels) with acute coronary syndrome that underwent near-infrared spectroscopy (NIRS)-IVUS and OCT imaging in their non-culprit vessels were included in the present analysis. The lumen borders annotated by expert analysts in 61,655 NIRS-IVUS and 62,334 OCT frames, and the side branches and calcific tissue identified in 10,000 NIRS-IVUS frames and 10,000 OCT frames, were used to train DL solutions for the automated extraction of these features. The trained DL solutions were used to process NIRS-IVUS and OCT images and their output was used by a dynamic time warping algorithm to co-register longitudinally the NIRS-IVUS and OCT images, while the circumferential registration of the IVUS and OCT was optimized through dynamic programming. On a test set of 77 vessels from 22 patients, the DL method showed high concordance with the expert analysts for the longitudinal and circumferential co-registration of the two imaging sets (concordance correlation coefficient >0.99 for the longitudinal and >0.90 for the circumferential co-registration). The Williams Index was 0.96 for longitudinal and 0.97 for circumferential co-registration, indicating a comparable performance to the analysts. The time needed for the DL pipeline to process imaging data from a vessel was <90s. Conclusion: The fully automated, DL-based framework introduced in this study for the co-registration of IVUS and OCT is fast and provides estimations that compare favorably to the expert analysts. These features renders it useful in research in the analysis of large-scale data collected in studies that incorporate multimodality imaging to characterize plaque composition.
Authors: You Lu, Dingji Wang, Kaifeng Huang, Bihuan Chen, Xin Peng
Abstract: Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and robustness of autonomous driving systems (ADSs). Despite the recent achievements in testing various ADS modules, little attention has been paid on the automated testing of traffic light detection models in ADSs. A common practice is to manually collect and label traffic light data. However, it is labor-intensive, and even impossible to collect diverse data under different driving environments. To address these problems, we propose and implement TigAug to automatically augment labeled traffic light images for testing traffic light detection models in ADSs. We construct two families of metamorphic relations and three families of transformations based on a systematic understanding of weather environments, camera properties, and traffic light properties. We use augmented images to detect erroneous behaviors of traffic light detection models by transformation-specific metamorphic relations, and to improve the performance of traffic light detection models by retraining. Large-scale experiments with four state-of-the-art traffic light detection models and two traffic light datasets have demonstrated that i) TigAug is effective in testing traffic light detection models, ii) TigAug is efficient in synthesizing traffic light images, and iii) TigAug generates traffic light images with acceptable naturalness.
Authors: Daghash K. Alqahtani, Maria A. Rodriguez, Muhammad Aamir Cheema, Hamid Rezatofighi, Adel N. Toosi
Abstract: Edge computing enables data processing closer to the source, significantly reducing latency an essential requirement for real-time vision-based analytics such as object detection in surveillance and smart city environments. However, these tasks place substantial demands on resource constrained edge devices, making the joint optimization of energy consumption and detection accuracy critical. To address this challenge, we propose ECORE, a framework that integrates multiple dynamic routing strategies including estimation based techniques and a greedy selection algorithm to direct image processing requests to the most suitable edge device-model pair. ECORE dynamically balances energy efficiency and detection performance based on object characteristics. We evaluate our approach through extensive experiments on real-world datasets, comparing the proposed routers against widely used baseline techniques. The evaluation leverages established object detection models (YOLO, SSD, EfficientDet) and diverse edge platforms, including Jetson Orin Nano, Raspberry Pi 4 and 5, and TPU accelerators. Results demonstrate that our proposed context-aware routing strategies can reduce energy consumption and latency by 45% and 49%, respectively, while incurring only a 2% loss in detection accuracy compared to accuracy-centric methods.
Authors: Maximilian Tschuchnig, Lukas Lamminger, Philipp Steininger, Michael Gadermayr
Abstract: Cone-Beam Computed Tomography (CBCT) is widely used for intraoperative imaging due to its rapid acquisition and low radiation dose. However, CBCT images typically suffer from artifacts and lower visual quality compared to conventional Computed Tomography (CT). A promising solution is synthetic CT (sCT) generation, where CBCT volumes are translated into the CT domain. In this work, we enhance sCT generation through multimodal learning by jointly leveraging intraoperative CBCT and preoperative CT data. To overcome the inherent misalignment between modalities, we introduce an end-to-end learnable registration module within the sCT pipeline. This model is evaluated on a controlled synthetic dataset, allowing precise manipulation of data quality and alignment parameters. Further, we validate its robustness and generalizability on two real-world clinical datasets. Experimental results demonstrate that integrating registration in multimodal sCT generation improves sCT quality, outperforming baseline multimodal methods in 79 out of 90 evaluation settings. Notably, the improvement is most significant in cases where CBCT quality is low and the preoperative CT is moderately misaligned.
Authors: Seungoh Han, Jaehoon Jang, Hyunsu Kim, Jaeheung Surh, Junhyung Kwak, Hyowon Ha, Kyungdon Joo
Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time novel view synthesis (NVS) with impressive quality in indoor scenes. However, achieving high-fidelity rendering requires meticulously captured images covering the entire scene, limiting accessibility for general users. We aim to develop a practical 3DGS-based NVS framework using simple panorama-style motion with a handheld camera (e.g., mobile device). While convenient, this rotation-dominant motion and narrow baseline make accurate camera pose and 3D point estimation challenging, especially in textureless indoor scenes. To address these challenges, we propose LighthouseGS, a novel framework inspired by the lighthouse-like sweeping motion of panoramic views. LighthouseGS leverages rough geometric priors, such as mobile device camera poses and monocular depth estimation, and utilizes the planar structures often found in indoor environments. We present a new initialization method called plane scaffold assembly to generate consistent 3D points on these structures, followed by a stable pruning strategy to enhance geometry and optimization stability. Additionally, we introduce geometric and photometric corrections to resolve inconsistencies from motion drift and auto-exposure in mobile devices. Tested on collected real and synthetic indoor scenes, LighthouseGS delivers photorealistic rendering, surpassing state-of-the-art methods and demonstrating the potential for panoramic view synthesis and object placement.
Authors: Mohammad Mahdi Derakhshani, Dheeraj Varghese, Marzieh Fadaee, Cees G. M. Snoek
Abstract: Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these introduce semantic drift, computational overhead, and cultural misalignment. We introduce NeoBabel, a novel multilingual image generation framework that sets a new Pareto frontier in performance, efficiency and inclusivity, supporting six languages: English, Chinese, Dutch, French, Hindi, and Persian. The model is trained using a combination of large-scale multilingual pretraining and high-resolution instruction tuning. To evaluate its capabilities, we expand two English-only benchmarks to multilingual equivalents: m-GenEval and m-DPG. NeoBabel achieves state-of-the-art multilingual performance while retaining strong English capability, scoring 0.75 on m-GenEval and 0.68 on m-DPG. Notably, it performs on par with leading models on English tasks while outperforming them by +0.11 and +0.09 on multilingual benchmarks, even though these models are built on multilingual base LLMs. This demonstrates the effectiveness of our targeted alignment training for preserving and extending crosslingual generalization. We further introduce two new metrics to rigorously assess multilingual alignment and robustness to code-mixed prompts. Notably, NeoBabel matches or exceeds English-only models while being 2-4x smaller. We release an open toolkit, including all code, model checkpoints, a curated dataset of 124M multilingual text-image pairs, and standardized multilingual evaluation protocols, to advance inclusive AI research. Our work demonstrates that multilingual capability is not a trade-off but a catalyst for improved robustness, efficiency, and cultural fidelity in generative AI.
Authors: Zhihao Chen, Tao Chen, Chenhui Wang, Qi Gao, Huidong Xie, Chuang Niu, Ge Wang, Hongming Shan
Abstract: Low-dose computed tomography (LDCT) reduces radiation exposure but often degrades image quality, potentially compromising diagnostic accuracy. Existing deep learning-based denoising methods focus primarily on pixel-level mappings, overlooking the potential benefits of high-level semantic guidance. Recent advances in vision-language models (VLMs) suggest that language can serve as a powerful tool for capturing structured semantic information, offering new opportunities to improve LDCT reconstruction. In this paper, we introduce LangMamba, a Language-driven Mamba framework for LDCT denoising that leverages VLM-derived representations to enhance supervision from normal-dose CT (NDCT). LangMamba follows a two-stage learning strategy. First, we pre-train a Language-guided AutoEncoder (LangAE) that leverages frozen VLMs to map NDCT images into a semantic space enriched with anatomical information. Second, we synergize LangAE with two key components to guide LDCT denoising: Semantic-Enhanced Efficient Denoiser (SEED), which enhances NDCT-relevant local semantic while capturing global features with efficient Mamba mechanism, and Language-engaged Dual-space Alignment (LangDA) Loss, which ensures that denoised images align with NDCT in both perceptual and semantic spaces. Extensive experiments on two public datasets demonstrate that LangMamba outperforms conventional state-of-the-art methods, significantly improving detail preservation and visual fidelity. Remarkably, LangAE exhibits strong generalizability to unseen datasets, thereby reducing training costs. Furthermore, LangDA loss improves explainability by integrating language-guided insights into image reconstruction and offers a plug-and-play fashion. Our findings shed new light on the potential of language as a supervisory signal to advance LDCT denoising. The code is publicly available on https://github.com/hao1635/LangMamba.
Authors: Wei Shen, Jiangbo Pei, Yi Peng, Xuchen Song, Yang Liu, Jian Peng, Haofeng Sun, Yunzhuo Hao, Peiyu Wang, Jianhao Zhang, Yahui Zhou
Abstract: We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cross-modal alignment for multimodal reasoning models. In addition, we introduce a unique indicator of reasoning capability, the entropy of critical reasoning tokens, which has proven highly effective for checkpoint selection during RL training. Skywork-R1V3 achieves state-of-the-art results on MMMU, significantly improving from 64.3% to 76.0%. This performance matches entry-level human capabilities. Remarkably, our RL-powered post-training approach enables even the 38B parameter model to rival top closed-source VLMs. The implementation successfully transfers mathematical reasoning to other subject-related reasoning tasks. We also include an analysis of curriculum learning and reinforcement finetuning strategies, along with a broader discussion on multimodal reasoning. Skywork-R1V3 represents a significant leap in multimodal reasoning, showcasing RL as a powerful engine for advancing open-source VLM capabilities.
Authors: Zhenghao Zhang, Shengfan Zhang, Zhichao Wei, Zuozhuo Dai, Siyu Zhu
Abstract: The current state-of-the-art methods for unsupervised video object segmentation (UVOS) require extensive training on video datasets with mask annotations, limiting their effectiveness in handling challenging scenarios. However, the Segment Anything Model (SAM) introduces a new prompt-driven paradigm for image segmentation, offering new possibilities. In this study, we investigate SAM's potential for UVOS through different prompt strategies. We then propose UVOSAM, a mask-free paradigm for UVOS that utilizes the STD-Net tracker. STD-Net incorporates a spatial-temporal decoupled deformable attention mechanism to establish an effective correlation between intra- and inter-frame features, remarkably enhancing the quality of box prompts in complex video scenes. Extensive experiments on the DAVIS2017-unsupervised and YoutubeVIS19\&21 datasets demonstrate the superior performance of UVOSAM without mask supervision compared to existing mask-supervised methods, as well as its ability to generalize to weakly-annotated video datasets. Code can be found at https://github.com/alibaba/UVOSAM.
Authors: Akio Kodaira, Chenfeng Xu, Toshiki Hazama, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Zhijian Liu, Masayoshi Tomizuka, Kurt Keutzer
Abstract: We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively.
Authors: Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano H\"oher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Chinmay Prabhakar, Ezequiel de la Rosa, Bastian Wittmann, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin Menten, Ivan Ezhov, Daniel Rueckert, Iris N. Vos, Ynte M. Ruigrok, Birgitta K. Velthuis, Hugo J. Kuijf, Pengcheng Shi, Wei Liu, Ting Ma, Maximilian R. Rokuss, Yannick Kirchhoff, Fabian Isensee, Klaus Maier-Hein, Chengcheng Zhu, Huilin Zhao, Philippe Bijlenga, Julien H\"ammerli, Catherine Wurster, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Hannah-Lea Handelsmann, Andrew Makmur, James Hallinan, Amrish Soundararajan, Bene Wiestler, Jan S. Kirschke, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Kwanseok Oh, Dahye Lee, Adam Hilbert, Orhun Utku Aydin, Dimitrios Rallios, Jana Rieger, Satoru Tanioka, Alexander Koch, Dietmar Frey, Abdul Qayyum, Moona Mazher, Steven Niederer, Nico Disch, Julius Holzschuh, Dominic LaBella, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Minghui Zhang, Xin You, Hanxiao Zhang, Guang-Zhong Yang, Yun Gu, Sinyoung Ra, Jongyun Hwang, Hyunjin Park, Junqiang Chen, Marek Wodzinski, Henning M\"uller, Nesrin Mansouri, Florent Autrusseau, Cansu Yal\c{c}in, Rachika E. Hamadache, Clara Lisazo, Joaquim Salvi, Adri\`a Casamitjana, Xavier Llad\'o, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Paula Casademunt, Adrian Galdran, Matteo Delucchi, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Adnan H. Siddiqui, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze
Abstract: The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neurovascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two non-invasive angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited datasets with annotations on CoW anatomy, especially for CTA. Therefore, we organized the TopCoW challenge with the release of an annotated CoW dataset. The TopCoW dataset is the first public dataset with voxel-level annotations for 13 CoW vessel components, enabled by virtual reality technology. It is also the first large dataset using 200 pairs of MRA and CTA from the same patients. As part of the benchmark, we invited submissions worldwide and attracted over 250 registered participants from six continents. The submissions were evaluated on both internal and external test datasets of 226 scans from over five centers. The top performing teams achieved over 90% Dice scores at segmenting the CoW components, over 80% F1 scores at detecting key CoW components, and over 70% balanced accuracy at classifying CoW variants for nearly all test sets. The best algorithms also showed clinical potential in classifying fetal-type posterior cerebral artery and locating aneurysms with CoW anatomy. TopCoW demonstrated the utility and versatility of CoW segmentation algorithms for a wide range of downstream clinical applications with explainability. The annotated datasets and best performing algorithms have been released as public Zenodo records to foster further methodological development and clinical tool building.
Authors: Haoyuan Li, Qi Hu, Binjia Zhou, You Yao, Jiacheng Lin, Kailun Yang, Peng Chen
Abstract: Visible-infrared image pairs provide complementary information, enhancing the reliability and robustness of object detection applications in real-world scenarios. However, most existing methods face challenges in maintaining robustness under complex weather conditions, which limits their applicability. Meanwhile, the reliance on attention mechanisms in modality fusion introduces significant computational complexity and storage overhead, particularly when dealing with high-resolution images. To address these challenges, we propose the Cross-modality Fusion Mamba with Weather-removal (CFMW) to augment stability and cost-effectiveness under adverse weather conditions. Leveraging the proposed Perturbation-Adaptive Diffusion Model (PADM) and Cross-modality Fusion Mamba (CFM) modules, CFMW is able to reconstruct visual features affected by adverse weather, enriching the representation of image details. With efficient architecture design, CFMW is 3 times faster than Transformer-style fusion (e.g., CFT). To bridge the gap in relevant datasets, we construct a new Severe Weather Visible-Infrared (SWVI) dataset, encompassing diverse adverse weather scenarios such as rain, haze, and snow. The dataset contains 64,281 paired visible-infrared images, providing a valuable resource for future research. Extensive experiments on public datasets (i.e., M3FD and LLVIP) and the newly constructed SWVI dataset conclusively demonstrate that CFMW achieves state-of-the-art detection performance. Both the dataset and source code will be made publicly available at https://github.com/lhy-zjut/CFMW.
Authors: Xiaogang Xu, Kun Zhou, Tao Hu, Jiafei Wu, Ruixing Wang, Hao Peng, Bei Yu
Abstract: Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and view-dependent components to enhance the performance of LLVE. We leverage dynamic cross-frame correspondences for the view-independent term (which primarily captures intrinsic appearance) and impose a scene-level continuity constraint on the view-dependent term (which mainly describes the shading condition) to achieve consistent and satisfactory decomposition results. To further ensure consistent decomposition, we introduce a dual-structure enhancement network featuring a cross-frame interaction mechanism. By supervising different frames simultaneously, this network encourages them to exhibit matching decomposition features. This mechanism can seamlessly integrate with encoder-decoder single-frame networks, incurring minimal additional parameter costs. Extensive experiments are conducted on widely recognized LLVE benchmarks, covering diverse scenarios. Our framework consistently outperforms existing methods, establishing a new SOTA performance.
Authors: Dongmyeong Lee, Amanda Adkins, Joydeep Biswas
Abstract: Mobile service robots can benefit from object-level understanding of their environments, including the ability to distinguish object instances and re-identify previously seen instances. Object re-identification is challenging across different viewpoints and in scenes with significant appearance variation arising from weather or lighting changes. Existing works on object re-identification either focus on specific classes or require foreground segmentation. Further, these methods, along with object re-identification datasets, have limited consideration of challenges such as outdoor scenes and illumination changes. To address this problem, we introduce CODa Re-ID: an in-the-wild object re-identification dataset containing 1,037,814 observations of 557 objects across 8 classes under diverse lighting conditions and viewpoints. Further, we propose CLOVER, a representation learning method for object observations that can distinguish between static object instances without requiring foreground segmentation. We also introduce MapCLOVER, a method for scalably summarizing CLOVER descriptors for use in object maps and matching new observations to summarized descriptors. Our results show that CLOVER achieves superior performance in static object re-identification under varying lighting conditions and viewpoint changes and can generalize to unseen instances and classes.
Authors: Wenxuan Li, Chongyu Qu, Xiaoxi Chen, Pedro R. A. S. Bassi, Yijia Shi, Yuxiang Lai, Qian Yu, Huimin Xue, Yixiong Chen, Xiaorui Lin, Yutong Tang, Yining Cao, Haoqi Han, Zheyuan Zhang, Jiawei Liu, Tiezheng Zhang, Yujiu Ma, Jincheng Wang, Guang Zhang, Alan Yuille, Zongwei Zhou
Abstract: We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes sourced from 112 hospitals across diverse populations, geographies, and facilities. AbdomenAtlas provides 673K high-quality masks of anatomical structures in the abdominal region annotated by a team of 10 radiologists with the help of AI algorithms. We start by having expert radiologists manually annotate 22 anatomical structures in 5,246 CT volumes. Following this, a semi-automatic annotation procedure is performed for the remaining CT volumes, where radiologists revise the annotations predicted by AI, and in turn, AI improves its predictions by learning from revised annotations. Such a large-scale, detailed-annotated, and multi-center dataset is needed for two reasons. Firstly, AbdomenAtlas provides important resources for AI development at scale, branded as large pre-trained models, which can alleviate the annotation workload of expert radiologists to transfer to broader clinical applications. Secondly, AbdomenAtlas establishes a large-scale benchmark for evaluating AI algorithms -- the more data we use to test the algorithms, the better we can guarantee reliable performance in complex clinical scenarios. An ISBI & MICCAI challenge named BodyMaps: Towards 3D Atlas of Human Body was launched using a subset of our AbdomenAtlas, aiming to stimulate AI innovation and to benchmark segmentation accuracy, inference efficiency, and domain generalizability. We hope our AbdomenAtlas can set the stage for larger-scale clinical trials and offer exceptional opportunities to practitioners in the medical imaging community. Codes, models, and datasets are available at https://www.zongweiz.com/dataset
Authors: Naichuan Zheng, Yuchen Du, Hailun Xia, Zeyu Liang
Abstract: For multimodal skeleton-based action recognition, Graph Convolutional Networks (GCNs) are effective models. Still, their reliance on floating-point computations leads to high energy consumption, limiting their applicability in battery-powered devices. While energy-efficient, Spiking Neural Networks (SNNs) struggle to model skeleton dynamics, leading to suboptimal solutions. We propose Signal-SGN (Spiking Graph Convolutional Network), which utilizes the temporal dimension of skeleton sequences as the spike time steps and represents features as multi-dimensional discrete stochastic signals for temporal-frequency domain feature extraction. It combines the 1D Spiking Graph Convolution (1D-SGC) module and the Frequency Spiking Convolution (FSC) module to extract features from the skeleton represented as spiking form. Additionally, the Multi-Scale Wavelet Transform Feature Fusion (MWTF) module is proposed to extract dynamic spiking features and capture frequency-specific characteristics, enhancing classification performance. Experiments across three large-scale datasets reveal Signal-SGN exceeding state-of-the-art SNN-based methods in accuracy and computational efficiency while attaining comparable performance with GCN methods and significantly reducing theoretical energy consumption.
Authors: Fan Zhao, Yijia Chen, Dianhan Xi, Yongying Liu, Jiaqi Wang, Shigeru Tabeta, Katsunori Mizuno
Abstract: Hermit crabs play a crucial role in coastal ecosystems by dispersing seeds, cleaning up debris, and disturbing soil. They serve as vital indicators of marine environmental health, responding to climate change and pollution. Traditional survey methods, like quadrat sampling, are labor-intensive, time-consuming, and environmentally dependent. This study presents an innovative approach combining UAV-based remote sensing with Super-Resolution Reconstruction (SRR) and the CRAB-YOLO detection network, a modification of YOLOv8s, to monitor hermit crabs. SRR enhances image quality by addressing issues such as motion blur and insufficient resolution, significantly improving detection accuracy over conventional low-resolution fuzzy images. The CRAB-YOLO network integrates three improvements for detection accuracy, hermit crab characteristics, and computational efficiency, achieving state-of-the-art (SOTA) performance compared to other mainstream detection models. The RDN networks demonstrated the best image reconstruction performance, and CRAB-YOLO achieved a mean average precision (mAP) of 69.5% on the SRR test set, a 40% improvement over the conventional Bicubic method with a magnification factor of 4. These results indicate that the proposed method is effective in detecting hermit crabs, offering a cost-effective and automated solution for extensive hermit crab monitoring, thereby aiding coastal benthos conservation.
Authors: Fan Zhao, Yongying Liu, Jiaqi Wang, Yijia Chen, Dianhan Xi, Xinlei Shao, Shigeru Tabeta, Katsunori Mizuno
Abstract: Underwater litter is widely spread across aquatic environments such as lakes, rivers, and oceans, significantly impacting natural ecosystems. Current monitoring technologies for detecting underwater litter face limitations in survey efficiency, cost, and environmental conditions, highlighting the need for efficient, consumer-grade technologies for automatic detection. This research introduces the Aerial-Aquatic Speedy Scanner (AASS) combined with Super-Resolution Reconstruction (SRR) and an improved YOLOv8 detection network. AASS enhances data acquisition efficiency over traditional methods, capturing high-quality images that accurately identify underwater waste. SRR improves image-resolution by mitigating motion blur and insufficient resolution, thereby enhancing detection tasks. Specifically, the RCAN model achieved the highest mean average precision (mAP) of 78.6% for detection accuracy on reconstructed images among the tested SRR models. With a magnification factor of 4, the SRR test set shows an improved mAP compared to the conventional bicubic set. These results demonstrate the effectiveness of the proposed method in detecting underwater litter.
Authors: Wenfeng Huang, Guoan Xu, Wenjing Jia, Stuart Perry, Guangwei Gao
Abstract: Images captured in challenging environments--such as nighttime, smoke, rainy weather, and underwater--often suffer from significant degradation, resulting in a substantial loss of visual quality. The effective restoration of these degraded images is critical for the subsequent vision tasks. While many existing approaches have successfully incorporated specific priors for individual tasks, these tailored solutions limit their applicability to other degradations. In this work, we propose a universal network architecture, dubbed ``ReviveDiff'', which can address various degradations and bring images back to life by enhancing and restoring their quality. Our approach is inspired by the observation that, unlike degradation caused by movement or electronic issues, quality degradation under adverse conditions primarily stems from natural media (such as fog, water, and low luminance), which generally preserves the original structures of objects. To restore the quality of such images, we leveraged the latest advancements in diffusion models and developed ReviveDiff to restore image quality from both macro and micro levels across some key factors determining image quality, such as sharpness, distortion, noise level, dynamic range, and color accuracy. We rigorously evaluated ReviveDiff on seven benchmark datasets covering five types of degrading conditions: Rainy, Underwater, Low-light, Smoke, and Nighttime Hazy. Our experimental results demonstrate that ReviveDiff outperforms the state-of-the-art methods both quantitatively and visually.
Authors: Camille Delgrange, Olga Demler, Samia Mora, Bjoern Menze, Ezequiel de la Rosa, Neda Davoudi
Abstract: Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and image-derived features to improve stroke risk prediction prior to onset. By leveraging large unannotated clinical datasets, the framework captures complementary and synergistic information across image and tabular data modalities. Our approach is based on a contrastive learning framework that couples contrastive language-image pretraining with an image-tabular matching module, to better align multimodal data representations in a shared latent space. The model is trained on the UK Biobank, which includes structural brain MRI and clinical data. We benchmark its performance against state-of-the-art unimodal and multimodal methods using tabular, image, and image-tabular combinations under diverse frozen and trainable model settings. The proposed model outperformed self-supervised tabular (image) methods by 2.6% (2.6%) in ROC-AUC and by 3.3% (5.6%) in balanced accuracy. Additionally, it showed a 7.6% increase in balanced accuracy compared to the best multimodal supervised model. Through interpretable tools, our approach demonstrated better integration of tabular and image data, providing richer and more aligned embeddings. Gradient-weighted Class Activation Mapping heatmaps further revealed activated brain regions commonly associated in the literature with brain aging, stroke risk, and clinical outcomes. This robust self-supervised multimodal framework surpasses state-of-the-art methods for stroke risk prediction and offers a strong foundation for future studies integrating diverse data modalities to advance clinical predictive modelling.
Authors: Minghao Fu, Hao Yu, Jie Shao, Junjie Zhou, Ke Zhu, Jianxin Wu
Abstract: Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration technique, reduces storage costs and enables potential inference acceleration by discretizing network weights and activations into a finite set of integer values. However, current quantization methods are often complex and sensitive, requiring extensive task-specific hyperparameters, where even a single misconfiguration can impair model performance, limiting generality across different models and tasks. In this paper, we propose Quantization without Tears (QwT), a method that simultaneously achieves quantization speed, accuracy, simplicity, and generality. The key insight of QwT is to incorporate a lightweight additional structure into the quantized network to mitigate information loss during quantization. This structure consists solely of a small set of linear layers, keeping the method simple and efficient. More importantly, it provides a closed-form solution, allowing us to improve accuracy effortlessly under 2 minutes. Extensive experiments across various vision, language, and multimodal tasks demonstrate that QwT is both highly effective and versatile. In fact, our approach offers a robust solution for network quantization that combines simplicity, accuracy, and adaptability, which provides new insights for the design of novel quantization paradigms. The code is publicly available at https://github.com/wujx2001/QwT
Authors: Guanjie Chen, Xinyu Zhao, Yucheng Zhou, Xiaoye Qu, Tianlong Chen, Yu Cheng
Abstract: Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference. Through systematic analysis, we identify the absence of long-range feature preservation mechanisms as the root cause of unstable feature propagation and perturbation sensitivity. To this end, we propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets. Theoretical spectral norm and visualization analysis demonstrate how LSCs stabilize feature dynamics. Skip-DiT architecture and its stabilized dynamic feature enable an efficient statical caching mechanism that reuses deep features across timesteps while updating shallow components. Extensive experiments across the image and video generation tasks demonstrate that Skip-DiT achieves: (1) 4.4 times training acceleration and faster convergence, (2) 1.5-2 times inference acceleration with negligible quality loss and high fidelity to the original output, outperforming existing DiT caching methods across various quantitative metrics. Our findings establish Long-Skip-Connections as critical architectural components for stable and efficient diffusion transformers. Codes are provided in the https://github.com/OpenSparseLLMs/Skip-DiT.
Authors: Chicago Y. Park, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov
Abstract: We present a concise derivation for several influential score-based diffusion models that relies on only a few textbook results. Diffusion models have recently emerged as powerful tools for generating realistic, synthetic signals -- particularly natural images -- and often play a role in state-of-the-art algorithms for inverse problems in image processing. While these algorithms are often surprisingly simple, the theory behind them is not, and multiple complex theoretical justifications exist in the literature. Here, we provide a simple and largely self-contained theoretical justification for score-based diffusion models that is targeted towards the signal processing community. This approach leads to generic algorithmic templates for training and generating samples with diffusion models. We show that several influential diffusion models correspond to particular choices within these templates and demonstrate that alternative, more straightforward algorithmic choices can provide comparable results. This approach has the added benefit of enabling conditional sampling without any likelihood approximation.
Authors: Zeyu Yang, Zijie Pan, Yuankun Yang, Xiatian Zhu, Li Zhang
Abstract: Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but struggle to generalize to novel trajectories due to limited viewpoints in driving videos. To tackle this challenge, we propose DriveX, a novel free-form driving view synthesis framework, that progressively distills generative prior into the 3D Gaussian model during its optimization. Within this framework, we utilize a video diffusion model to refine the degraded novel trajectory renderings from the in-training Gaussian model, while the restored videos in turn serve as additional supervision for optimizing the 3D Gaussian. Concretely, we craft an inpainting-based video restoration task, which can disentangle the identification of degraded regions from the generative capability of the diffusion model and remove the need of simulating specific degraded pattern in the training of the diffusion model. To further enhance the consistency and fidelity of generated contents, the pseudo ground truth is progressively updated with gradually improved novel trajectory rendering, allowing both components to co-adapt and reinforce each other while minimizing the disruption on the optimization. By tightly integrating 3D scene representation with generative prior, DriveX achieves high-quality view synthesis beyond recorded trajectories in real time--unlocking new possibilities for flexible and realistic driving simulations on free-form trajectories.
Authors: Rongkun Xue, Jinouwen Zhang, Yazhe Niu, Dazhong Shen, Bingqi Ma, Yu Liu, Jing Yang
Abstract: Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous generation model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. This framework enables the flexible selection of feature hierarchies tailored to specific downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model based methods, including 78% top-1 accuracy on ImageNet at a resolution of 64*64. Extensive ablation studies, including out-of-distribution evaluations, further validate the effectiveness of our approach.PRG is available at https://github.com/opendilab/PRG.
Authors: Ziqi Pang, Tianyuan Zhang, Fujun Luan, Yunze Man, Hao Tan, Kai Zhang, William T. Freeman, Yu-Xiong Wang
Abstract: We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a predefined generation order, RandAR removes this inductive bias, unlocking new capabilities in decoder-only generation. Our essential design enables random order by inserting a "position instruction token" before each image token to be predicted, representing the spatial location of the next image token. Trained on randomly permuted token sequences -- a more challenging task than fixed-order generation, RandAR achieves comparable performance to its conventional raster-order counterpart. More importantly, decoder-only transformers trained from random orders acquire new capabilities. For the efficiency bottleneck of AR models, RandAR adopts parallel decoding with KV-Cache at inference time, enjoying 2.5x acceleration without sacrificing generation quality. Additionally, RandAR supports inpainting, outpainting and resolution extrapolation in a zero-shot manner. We hope RandAR inspires new directions for decoder-only visual generation models and broadens their applications across diverse scenarios. Our project page is at https://rand-ar.github.io/.
Authors: Qing Zhang, Zehao Chen, Jinguang Tong, Jing Zhang, Jie Hong, Xuesong Li
Abstract: Despite recent advances in text-to-3D generation techniques, current methods often suffer from geometric inconsistencies, commonly referred to as the Janus Problem. This paper identifies the root cause of the Janus Problem: viewpoint generation bias in diffusion models, which creates a significant gap between the actual generated viewpoint and the expected one required for optimizing the 3D model. To address this issue, we propose a tuning-free approach called the Attention and CLIP Guidance (ACG) mechanism. ACG enhances desired viewpoints by adaptively controlling cross-attention maps, employs CLIP-based view-text similarities to filter out erroneous viewpoints, and uses a coarse-to-fine optimization strategy with staged prompts to progressively refine 3D generation. Extensive experiments demonstrate that our method significantly reduces the Janus Problem without compromising generation speed, establishing ACG as an efficient, plug-and-play component for existing text-to-3D frameworks.
Authors: Jaeyoon Kim, Yoonki Cho, Taeyoung Kim, Sung-Eui Yoon
Abstract: Nearest neighbor (NN) graph based visual re-ranking has emerged as a powerful approach for improving retrieval accuracy, offering the advantages of effectively exploring high-dimensional manifolds without requiring additional fine-tuning. However, the effectiveness of NN graph-based re-ranking is fundamentally constrained by the quality of its edge connectivity, as incorrect connections between dissimilar (negative) images frequently occur. This is known as a noisy edge problem, which hinders the re-ranking performance of existing techniques and limits their potential. To remedy this issue, we propose a complementary denoising method based on Continuous Conditional Random Fields (C-CRF) that leverages statistical distances derived from similarity-based distributions. As a pre-processing step for enhancing NN graph-based retrieval, our approach constructs fully connected cliques around each anchor image and employs a novel statistical distance metric to robustly alleviate noisy edges before re-ranking while achieving efficient processing through offline computation. Extensive experimental results demonstrate that our method consistently improves three different NN graph-based re-ranking approaches, yielding significant gains in retrieval accuracy.
Authors: Austin T. Wang, ZeMing Gong, Angel X. Chang
Abstract: 3D visual grounding (3DVG) involves localizing entities in a 3D scene referred to by natural language text. Such models are useful for embodied AI and scene retrieval applications, which involve searching for objects or patterns using natural language descriptions. While recent works have focused on LLM-based scaling of 3DVG datasets, these datasets do not capture the full range of potential prompts which could be specified in the English language. To ensure that we are scaling up and testing against a useful and representative set of prompts, we propose a framework for linguistically analyzing 3DVG prompts and introduce Visual Grounding with Diverse Language in 3D (ViGiL3D), a diagnostic dataset for evaluating visual grounding methods against a diverse set of language patterns. We evaluate existing open-vocabulary 3DVG methods to demonstrate that these methods are not yet proficient in understanding and identifying the targets of more challenging, out-of-distribution prompts, toward real-world applications.
Authors: Cecilia Curreli, Dominik Muhle, Abhishek Saroha, Zhenzhang Ye, Riccardo Marin, Daniel Cremers
Abstract: Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected limb stretching and jitter. To address this, we introduce SkeletonDiffusion, a latent diffusion model that embeds an explicit inductive bias on the human body within its architecture and training. Our model is trained with a novel nonisotropic Gaussian diffusion formulation that aligns with the natural kinematic structure of the human skeleton. Results show that our approach outperforms conventional isotropic alternatives, consistently generating realistic predictions while avoiding artifacts such as limb distortion. Additionally, we identify a limitation in commonly used diversity metrics, which may inadvertently favor models that produce inconsistent limb lengths within the same sequence. SkeletonDiffusion sets a new benchmark on real-world datasets, outperforming various baselines across multiple evaluation metrics. Visit our project page at https://ceveloper.github.io/publications/skeletondiffusion/ .
URLs: https://ceveloper.github.io/publications/skeletondiffusion/
Authors: Sihyun Yu, Meera Hahn, Dan Kondratyuk, Jinwoo Shin, Agrim Gupta, Jos\'e Lezama, Irfan Essa, David Ross, Jonathan Huang
Abstract: Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.
Authors: Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, John Lee, Jenq-Neng Hwang, Lei Li
Abstract: In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose BayesGenie, an off-the-shelf approach that integrates Large Language Models (LLMs) with Bayesian Optimization to facilitate precise and user-friendly image editing. Our method enables users to modify images through natural language descriptions without manual area marking, while preserving the original image's semantic integrity. Unlike existing techniques that require extensive pre-training or fine-tuning, our approach demonstrates remarkable adaptability across various LLMs through its model-agnostic design. BayesGenie employs an adapted Bayesian optimization strategy to automatically refine the inference process parameters, achieving high-precision image editing with minimal user intervention. Through extensive experiments across diverse scenarios, we demonstrate that our framework significantly outperforms existing methods in both editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.
Authors: Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Vision-Language Models (VLMs) have demonstrated impressive multimodal capabilities in learning joint representations of visual and textual data, making them powerful tools for tasks such as Compositional Zero-Shot Learning (CZSL). CZSL requires models to generalize to novel combinations of visual primitives--such as attributes and objects--that were not explicitly encountered during training. Recent works in prompting for CZSL have focused on modifying inputs for the text encoder, often using static prompts that do not change across varying visual contexts. However, these approaches struggle to fully capture varying visual contexts, as they focus on text adaptation rather than leveraging visual features for compositional reasoning. To address this, we propose a Visual Adaptive Prompting System (VAPS) that leverages a learnable visual prompt repository and similarity-based retrieval mechanism within the framework of VLMs to bridge the gap between semantic and visual features. Our method introduces a dynamic visual prompt repository mechanism that selects the most relevant attribute and object prompts based on the visual features of the image. Our proposed system includes a visual prompt adapter that encourages the model to learn a more generalizable embedding space. Experiments on three CZSL benchmarks, across both closed and open-world scenarios, demonstrate state-of-the-art results.
Authors: Zhengxuan Zhang, Yin Wu, Yuyu Luo, Nan Tang
Abstract: Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language models (MLLMs) such as GPT-4o achieve strong performance on VQA tasks, they frequently fall short in accessing domain-specific or the latest knowledge. To mitigate this issue, retrieval-augmented generation (RAG) leveraging external knowledge bases (KBs), referred to as KB-VQA, emerges as a promising approach. Nevertheless, conventional unimodal retrieval techniques, which translate images into textual descriptions, often result in the loss of critical visual details. To address these challenges, this study presents two key innovations. First, we introduce fine-grained knowledge units that consist of multimodal data fragments (e.g. text fragments, entity images, and so on) in a structured manner. Rather than merely refining retrieval mechanisms, we prioritize the systematic organization and management of these knowledge units, ensuring that the structuring process itself enhances retrieval quality. Second, we propose a knowledge unit retrieval-augmented generation framework (KU-RAG) that seamlessly integrates fine-grained retrieval with MLLMs. Our KU-RAG framework not only ensures precise retrieval of relevant knowledge but also enhances reasoning capabilities through a knowledge correction chain. Experimental results demonstrate that our approach consistently outperforms existing KB-VQA methods across four benchmarks, achieving an average improvement of approximately 3% and up to 11% in the best case.
Authors: Zihan Huang, Wei Fang, Tong Bu, Peng Xue, Zecheng Hao, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang
Abstract: Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.
Authors: Sunghyun Ahn, Youngwan Jo, Kijung Lee, Sein Kwon, Inpyo Hong, Sanghyun Park
Abstract: Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments. Consequently, users should retrain models or develop separate AI models for new environments, which requires expertise in machine learning, high-performance hardware, and extensive data collection, limiting the practical usability of VAD. To address these challenges, this study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model. C-VAD considers user-defined text as an abnormal event and detects frames containing a specified event in a video. We effectively implemented AnyAnomaly using a context-aware visual question answering without fine-tuning the large vision language model. To validate the effectiveness of the proposed model, we constructed C-VAD datasets and demonstrated the superiority of AnyAnomaly. Furthermore, our approach showed competitive performance on VAD benchmark datasets, achieving state-of-the-art results on the UBnormal dataset and outperforming other methods in generalization across all datasets. Our code is available online at github.com/SkiddieAhn/Paper-AnyAnomaly.
Authors: Miao Zhang, Zhenlong Fang, Tianyi Wang, Qian Zhang, Shuai Lu, Junfeng Jiao, Tianyu Shi
Abstract: Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretability issues.These tasks are compounded when deep environment understanding, agent coordination and dynamic optimization are required. While Large Language Model (LLM) enhanced methods have shown promise in generalization and interoperability, they often neglect necessary multi-agent coordination. Therefore, we introduce the Cascading Cooperative Multi-agent (CCMA) framework, integrating RL for individual interactions, a fine-tuned LLM for regional cooperation, a reward function for global optimization, and the Retrieval-augmented Generation mechanism to dynamically optimize decision-making across complex driving scenarios. Our experiments demonstrate that the CCMA outperforms existing RL methods, demonstrating significant improvements in both micro and macro-level performance in complex driving environments.
Authors: Mikey Shechter, Yair Carmon
Abstract: We introduce Filter Like You Test (FLYT), an algorithm for curating large-scale vision-language datasets that learns the usefulness of each data point as a pretraining example. FLYT trains a scoring model that learns to weigh each example's features using gradient signals from downstream tasks training sets. Based on FLYT, we implement Mixing-FLYT (M-FLYT), which takes the per-example scores generated by different scoring methods as features, and learns to unify them into a single score. FLYT naturally produces a distribution over the training examples, which we leverage through Soft Cap Sampling (SCS), a strategy for obtaining a filtered pretraining dataset from per-example probabilities that samples examples while preventing over-representation through a repetition penalty. Using these methods, we achieve 40.1% ImageNet zero-shot accuracy on the DataComp medium scale filtering benchmark, a 2% absolute accuracy increase over all previous results and a 5.5% increase over results that - like us - use only public resources. Our approach also yields 37.7\% on the average of 38 DataComp evaluation tasks, outperforming previous public-resource approaches by 0.4\%.
Authors: Haoxuan Wang, Jinlong Peng, Qingdong He, Hao Yang, Ying Jin, Jiafu Wu, Xiaobin Hu, Yanjie Pan, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang
Abstract: With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing. Although existing methods can guide generation beyond text prompts, the challenge of effectively combining multiple conditional inputs while maintaining consistency with all of them remains unsolved. To address this, we introduce UniCombine, a DiT-based multi-conditional controllable generative framework capable of handling any combination of conditions, including but not limited to text prompts, spatial maps, and subject images. Specifically, we introduce a novel Conditional MMDiT Attention mechanism and incorporate a trainable LoRA module to build both the training-free and training-based versions. Additionally, we propose a new pipeline to construct SubjectSpatial200K, the first dataset designed for multi-conditional generative tasks covering both the subject-driven and spatially-aligned conditions. Extensive experimental results on multi-conditional generation demonstrate the outstanding universality and powerful capability of our approach with state-of-the-art performance.
Authors: Sayed Pedram Haeri Boroujeni, Niloufar Mehrabi, Fatemeh Afghah, Connor Peter McGrath, Danish Bhatkar, Mithilesh Anil Biradar, Abolfazl Razi
Abstract: Fire and smoke phenomena pose a significant threat to the natural environment, ecosystems, and global economy, as well as human lives and wildlife. In this particular circumstance, there is a demand for more sophisticated and advanced technologies to implement an effective strategy for early detection, real-time monitoring, and minimizing the overall impacts of fires on ecological balance and public safety. Recently, the rapid advancement of Artificial Intelligence (AI) and Computer Vision (CV) frameworks has substantially revolutionized the momentum for developing efficient fire management systems. However, these systems extensively rely on the availability of adequate and high-quality fire and smoke data to create proficient Machine Learning (ML) methods for various tasks, such as detection and monitoring. Although fire and smoke datasets play a critical role in training, evaluating, and testing advanced Deep Learning (DL) models, a comprehensive review of the existing datasets is still unexplored. For this purpose, we provide an in-depth review to systematically analyze and evaluate fire and smoke datasets collected over the past 20 years. We investigate the characteristics of each dataset, including type, size, format, collection methods, and geographical diversities. We also review and highlight the unique features of each dataset, such as imaging modalities (RGB, thermal, infrared) and their applicability for different fire management tasks (classification, segmentation, detection). Furthermore, we summarize the strengths and weaknesses of each dataset and discuss their potential for advancing research and technology in fire management. Ultimately, we conduct extensive experimental analyses across different datasets using several state-of-the-art algorithms, such as ResNet-50, DeepLab-V3, and YoloV8.
Authors: Xiang Li, Heqian Qiu, Lanxiao Wang, Hanwen Zhang, Chenghao Qi, Linfeng Han, Huiyu Xiong, Hongliang Li
Abstract: With the rapid development of artificial intelligence technologies and wearable devices, egocentric vision understanding has emerged as a new and challenging research direction, gradually attracting widespread attention from both academia and industry. Egocentric vision captures visual and multimodal data through cameras or sensors worn on the human body, offering a unique perspective that simulates human visual experiences. This paper provides a comprehensive survey of the research on egocentric vision understanding, systematically analyzing the components of egocentric scenes and categorizing the tasks into four main areas: subject understanding, object understanding, environment understanding, and hybrid understanding. We explore in detail the sub-tasks within each category. We also summarize the main challenges and trends currently existing in the field. Furthermore, this paper presents an overview of high-quality egocentric vision datasets, offering valuable resources for future research. By summarizing the latest advancements, we anticipate the broad applications of egocentric vision technologies in fields such as augmented reality, virtual reality, and embodied intelligence, and propose future research directions based on the latest developments in the field.
Authors: Yufei Shi, Weilong Yan, Gang Xu, Yumeng Li, Yucheng Chen, Zhenxi Li, Fei Richard Yu, Ming Li, Si Yong Yeo
Abstract: Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as "Wilson is receiving chemotherapy" or "Tom is discussing with Sarah", limiting their applicability in smart healthcare and smart home environments. To address this limitation, we propose a one-shot learning framework PVChat, the first personalized ViLLM that enables subject-aware question answering (QA) from a single video for each subject. Our approach optimizes a Mixture-of-Heads (MoH) enhanced ViLLM on a synthetically augmented video-QA dataset, leveraging a progressive image-to-video learning strategy. Specifically, we introduce an automated augmentation pipeline that synthesizes identity-preserving positive samples and retrieves hard negatives from existing video corpora, generating a diverse training dataset with four QA types: existence, appearance, action, and location inquiries. To enhance subject-specific learning, we propose a ReLU Routing MoH attention mechanism, alongside two novel objectives: (1) Smooth Proximity Regularization for progressive learning through exponential distance scaling and (2) Head Activation Enhancement for balanced attention routing. Finally, we adopt a two-stage training strategy, transitioning from image pre-training to video fine-tuning, enabling a gradual learning process from static attributes to dynamic representations. We evaluate PVChat on diverse datasets covering medical scenarios, TV series, anime, and real-world footage, demonstrating its superiority in personalized feature understanding after learning from a single video, compared to state-of-the-art ViLLMs.
Authors: Kun Li, Jianhui Wang, Miao Zhang, Xueqian Wang
Abstract: Generative AI has significantly advanced text-driven image generation, but it still faces challenges in producing outputs that consistently align with evolving user preferences and intents, particularly in multi-turn dialogue scenarios. In this research, We present a Visual Co-Adaptation (VCA) framework that incorporates human-in-the-loop feedback, utilizing a well-trained reward model specifically designed to closely align with human preferences. Using a diverse multi-turn dialogue dataset, the framework applies multiple reward functions (such as diversity, consistency, and preference feedback) to refine the diffusion model through LoRA, effectively optimizing image generation based on user input. We also constructed multi-round dialogue datasets with prompts and image pairs that well-fit user intent. Experiments show the model achieves 508 wins in human evaluation, outperforming DALL-E 3 (463 wins) and others. It also achieves 3.4 rounds in dialogue efficiency (vs. 13.7 for DALL-E 3) and excels in metrics like LPIPS (0.15) and BLIP (0.59). Various experiments demonstrate the effectiveness of the proposed method over state-of-the-art baselines, with significant improvements in image consistency and alignment with user intent.
Authors: Yuheng Feng, Jianhui Wang, Kun Li, Sida Li, Tianyu Shi, Haoyue Han, Miao Zhang, Xueqian Wang
Abstract: Although text-to-image generation technologies have made significant advancements, they still face challenges when dealing with ambiguous prompts and aligning outputs with user intent.Our proposed framework, TDRI (Two-Phase Dialogue Refinement and Co-Adaptation), addresses these issues by enhancing image generation through iterative user interaction. It consists of two phases: the Initial Generation Phase, which creates base images based on user prompts, and the Interactive Refinement Phase, which integrates user feedback through three key modules. The Dialogue-to-Prompt (D2P) module ensures that user feedback is effectively transformed into actionable prompts, which improves the alignment between user intent and model input. By evaluating generated outputs against user expectations, the Feedback-Reflection (FR) module identifies discrepancies and facilitates improvements. In an effort to ensure consistently high-quality results, the Adaptive Optimization (AO) module fine-tunes the generation process by balancing user preferences and maintaining prompt fidelity. Experimental results show that TDRI outperforms existing methods by achieving 33.6% human preference, compared to 6.2% for GPT-4 augmentation, and the highest CLIP and BLIP alignment scores (0.338 and 0.336, respectively). In iterative feedback tasks, user satisfaction increased to 88% after 8 rounds, with diminishing returns beyond 6 rounds. Furthermore, TDRI has been found to reduce the number of iterations and improve personalization in the creation of fashion products. TDRI exhibits a strong potential for a wide range of applications in the creative and industrial domains, as it streamlines the creative process and improves alignment with user preferences
Authors: Chenxi Xie, Minghan Li, Hui Zeng, Jun Luo, Lei Zhang
Abstract: High-resolution semantic segmentation is essential for applications such as image editing, bokeh imaging, AR/VR, etc. Unfortunately, existing datasets often have limited resolution and lack precise mask details and boundaries. In this work, we build a large-scale, matting-level semantic segmentation dataset, named MaSS13K, which consists of 13,348 real-world images, all at 4K resolution. MaSS13K provides high-quality mask annotations of a number of objects, which are categorized into seven categories: human, vegetation, ground, sky, water, building, and others. MaSS13K features precise masks, with an average mask complexity 20-50 times higher than existing semantic segmentation datasets. We consequently present a method specifically designed for high-resolution semantic segmentation, namely MaSSFormer, which employs an efficient pixel decoder that aggregates high-level semantic features and low-level texture features across three stages, aiming to produce high-resolution masks with minimal computational cost. Finally, we propose a new learning paradigm, which integrates the high-quality masks of the seven given categories with pseudo labels from new classes, enabling MaSSFormer to transfer its accurate segmentation capability to other classes of objects. Our proposed MaSSFormer is comprehensively evaluated on the MaSS13K benchmark together with 14 representative segmentation models. We expect that our meticulously annotated MaSS13K dataset and the MaSSFormer model can facilitate the research of high-resolution and high-quality semantic segmentation. Datasets and codes can be found at https://github.com/xiechenxi99/MaSS13K.
Authors: Hang Guo, Yawei Li, Taolin Zhang, Jiangshan Wang, Tao Dai, Shu-Tao Xia, Luca Benini
Abstract: Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7$\times$ with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.
Authors: Haruya Ishikawa, Yoshimitsu Aoki
Abstract: Semi-supervised semantic segmentation (SS-SS) aims to mitigate the heavy annotation burden of dense pixel labeling by leveraging abundant unlabeled images alongside a small labeled set. While current consistency regularization methods achieve strong results, they often overlook a critical challenge: the precise delineation of object boundaries. In this paper, we propose BoundMatch, a novel multi-task SS-SS framework that explicitly integrates semantic boundary detection into a teacher-student consistency regularization pipeline. Our core mechanism, Boundary Consistency Regularized Multi-Task Learning (BCRM), enforces prediction agreement between teacher and student models on both segmentation masks and detailed semantic boundaries. To further enhance performance and sharpen boundaries, BoundMatch incorporates two lightweight fusion modules: Boundary-Semantic Fusion (BSF) injects learned boundary cues into the segmentation decoder, while Spatial Gradient Fusion (SGF) refines boundary predictions using mask gradients, leading to higher-quality boundary pseudo-labels. This framework is built upon SAMTH, a strong teacher-student baseline featuring a Harmonious Batch Normalization (HBN) update strategy for improved stability. Extensive experiments on diverse urban-driving scene datasets including Cityscapes, BDD100K, and SYNTHIA show that BoundMatch achieves competitive performance against current state-of-the-art methods. Our approach achieves state-of-the-art results on the new benchmark with DINOv2 foundation model. We further validate our approach's generalizability on Pascal VOC and ADE20K datasets. Ablation studies highlight BoundMatch's ability to improve boundary-specific evaluation metrics, its effectiveness in realistic large-scale unlabeled data scenarios, and applicability to lightweight architectures for mobile deployment.
Authors: Mahir Gulzar, Yar Muhammad, Naveed Muhammad
Abstract: Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic participants). This paper presents a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements. We follow the famous encoder-interactor-decoder architecture where the encoder encodes scene context using lightweight Gated Recurrent Units, the interactor applies cross-context attention over encoded scene features and graph goal proposals, and the decoder regresses multimodal trajectories via Laplacian Mixture Density Network from the aggregated encodings. Using cross-attention over graph-based goal proposals gives robust trajectory estimates since the model learns to attend to future goal-relevant scene elements for the intended agent. We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
Authors: Pengfei Zhang, Shouqing Jia
Abstract: Denoising Diffusion Probabilistic Models (DDPM) process images as a whole. Since adjacent pixels are highly likely to belong to the same object, we propose the Heat Diffusion Model (HDM) to further preserve image details and generate more realistic images. HDM essentially is a DDPM that incorporates an attention mechanism between pixels. In HDM, the discrete form of the two-dimensional heat equation is integrated into the diffusion and generation formulas of DDPM, enabling the model to compute relationships between neighboring pixels during image processing. Our experiments demonstrate that HDM can generate higher-quality samples compared to models such as DDPM, Consistency Diffusion Models (CDM), Latent Diffusion Models (LDM), and Vector Quantized Generative Adversarial Networks (VQGAN).
Authors: Bahram Jafrasteh, Wei Peng, Cheng Wan, Yimin Luo, Ehsan Adeli, Qingyu Zhao
Abstract: Generative models enhance neuroimaging through data augmentation, quality improvement, and rare condition studies. Despite advances in realistic synthetic MRIs, evaluations focus on texture and perception, lacking sensitivity to crucial anatomical fidelity. This study proposes a new metric, called WASABI (Wasserstein-Based Anatomical Brain Index), to assess the anatomical realism of synthetic brain MRIs. WASABI leverages \textit{SynthSeg}, a deep learning-based brain parcellation tool, to derive volumetric measures of brain regions in each MRI and uses the multivariate Wasserstein distance to compare distributions between real and synthetic anatomies. Based on controlled experiments on two real datasets and synthetic MRIs from five generative models, WASABI demonstrates higher sensitivity in quantifying anatomical discrepancies compared to traditional image-level metrics, even when synthetic images achieve near-perfect visual quality. Our findings advocate for shifting the evaluation paradigm beyond visual inspection and conventional metrics, emphasizing anatomical fidelity as a crucial benchmark for clinically meaningful brain MRI synthesis. Our code is available at https://github.com/BahramJafrasteh/wasabi-mri.
Authors: Seraj Al Mahmud Mostafa, Chenxi Wang, Jia Yue, Yuta Hozumi, Jianwu Wang
Abstract: Object localization in satellite imagery is particularly challenging due to the high variability of objects, low spatial resolution, and interference from noise and dominant features such as clouds and city lights. In this research, we focus on three satellite datasets: upper atmospheric Gravity Waves (GW), mesospheric Bores (Bore), and Ocean Eddies (OE), each presenting its own unique challenges. These challenges include the variability in the scale and appearance of the main object patterns, where the size, shape, and feature extent of objects of interest can differ significantly. To address these challenges, we introduce YOLO-DCAP, a novel enhanced version of YOLOv5 designed to improve object localization in these complex scenarios. YOLO-DCAP incorporates a Multi-scale Dilated Residual Convolution (MDRC) block to capture multi-scale features at scale with varying dilation rates, and an Attention-aided Spatial Pooling (AaSP) module to focus on the global relevant spatial regions, enhancing feature selection. These structural improvements help to better localize objects in satellite imagery. Experimental results demonstrate that YOLO-DCAP significantly outperforms both the YOLO base model and state-of-the-art approaches, achieving an average improvement of 20.95% in mAP50 and 32.23% in IoU over the base model, and 7.35% and 9.84% respectively over state-of-the-art alternatives, consistently across all three satellite datasets. These consistent gains across all three satellite datasets highlight the robustness and generalizability of the proposed approach. Our code is open sourced at https://github.com/AI-4-atmosphere-remote-sensing/satellite-object-localization.
URLs: https://github.com/AI-4-atmosphere-remote-sensing/satellite-object-localization.
Authors: Linshuang Diao, Dayong Ren, Sensen Song, Yurong Qian
Abstract: State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing PointMamba-based methods depend on complex token ordering and random masking, which disrupt spatial continuity and local semantic correlations. We propose ZigzagPointMamba to tackle these challenges. The core of our approach is a simple zigzag scan path that globally sequences point cloud tokens, enhancing spatial continuity by preserving the proximity of spatially adjacent point tokens. Nevertheless, random masking undermines local semantic modeling in self-supervised learning. To address this, we introduce a Semantic-Siamese Masking Strategy (SMS), which masks semantically similar tokens to facilitate reconstruction by integrating local features of original and similar tokens. This overcomes the dependence on isolated local features and enables robust global semantic modeling. Our pre-trained ZigzagPointMamba weights significantly improve downstream tasks, achieving a 1.59% mIoU gain on ShapeNetPart for part segmentation, a 0.4% higher accuracy on ModelNet40 for classification, and 0.19%, 1.22%, and 0.72% higher accuracies respectively for the classification tasks on the OBJ-BG, OBJ-ONLY, and PB-T50-RS subsets of ScanObjectNN.
Authors: Yuka Ogino, Takahiro Toizumi, Atsushi Ito
Abstract: Low-Light Image Enhancement (LLIE) is crucial for improving both human perception and computer vision tasks. This paper addresses two challenges in zero-reference LLIE: obtaining perceptually 'good' images using the Contrastive Language-Image Pre-Training (CLIP) model and maintaining computational efficiency for high-resolution images. We propose CLIP-Utilized Reinforcement learning-based Visual image Enhancement (CURVE). CURVE employs a simple image processing module which adjusts global image tone based on B\'ezier curve and estimates its processing parameters iteratively. The estimator is trained by reinforcement learning with rewards designed using CLIP text embeddings. Experiments on low-light and multi-exposure datasets demonstrate the performance of CURVE in terms of enhancement quality and processing speed compared to conventional methods.
Authors: Chuyun Deng, Na Liu, Wei Xie, Lianming Xu, Li Wang
Abstract: Radio maps reflect the spatial distribution of signal strength and are essential for applications like smart cities, IoT, and wireless network planning. However, reconstructing accurate radio maps from sparse measurements remains challenging. Traditional interpolation and inpainting methods lack environmental awareness, while many deep learning approaches depend on detailed scene data, limiting generalization. To address this, we propose MARS, a Multi-scale Aware Radiomap Super-resolution method that combines CNNs and Transformers with multi-scale feature fusion and residual connections. MARS focuses on both global and local feature extraction, enhancing feature representation across different receptive fields and improving reconstruction accuracy. Experiments across different scenes and antenna locations show that MARS outperforms baseline models in both MSE and SSIM, while maintaining low computational cost, demonstrating strong practical potential.
Authors: Leon Mayer, Tim R\"adsch, Dominik Michael, Lucas Luttner, Amine Yamlahi, Evangelia Christodoulou, Patrick Godau, Marcel Knopp, Annika Reinke, Fiona Kolbinger, Lena Maier-Hein
Abstract: While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain performance. In this work, we present the first large-scale study assessing the capabilities of Vision Language Models (VLMs) for endoscopic tasks with a specific focus on laparoscopic surgery. Using a diverse set of state-of-the-art models, multiple surgical datasets, and extensive human reference annotations, we address three key research questions: (1) Can current VLMs solve basic perception tasks on surgical images? (2) Can they handle advanced frame-based endoscopic scene understanding tasks? and (3) How do specialized medical VLMs compare to generalist models in this context? Our results reveal that VLMs can effectively perform basic surgical perception tasks, such as object counting and localization, with performance levels comparable to general domain tasks. However, their performance deteriorates significantly when the tasks require medical knowledge. Notably, we find that specialized medical VLMs currently underperform compared to generalist models across both basic and advanced surgical tasks, suggesting that they are not yet optimized for the complexity of surgical environments. These findings highlight the need for further advancements to enable VLMs to handle the unique challenges posed by surgery. Overall, our work provides important insights for the development of next-generation endoscopic AI systems and identifies key areas for improvement in medical visual language models.
Authors: Yanzhe Chen (Yen-chieh Chan), Huasong Zhong, Yan Li, Zhenheng Yang
Abstract: Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existing codebook-based methods either rely on small vocabularies (~16K entries) that lack fine-grained semantics or naively scale up, resulting in low token utilization and unstable training. We propose UniCode$^2$, a cascaded codebook framework enabling large-scale, semantically aligned, and stable visual tokenization. By clustering millions of SigLIP sequence embeddings, we build a 500K-entry codebook that preserves vision-language alignment while expanding capacity. Stability is ensured via a cascaded design: a frozen codebook anchors the embedding space, and a trainable codebook refines task-specific semantics. This decoupling promotes high utilization and robust learning. Moreover, the alignment of our visual tokens with textual semantics enables seamless integration with pretrained diffusion decoders, supporting high-quality visual synthesis with minimal adaptation. UniCode^2 delivers strong performance across diverse benchmarks, demonstrating the viability of scaling visual token spaces without sacrificing stability, semantics, or modularity.
Authors: Yujia Liang, Jile Jiao, Xuetao Feng, Zixuan Ye, Yuan Wang, Zhicheng Wang
Abstract: Video Large Language Models (VideoLLMs) have demonstrated remarkable understanding capabilities, but are found struggling to tackle multi-shot scenarios,e.g., video clips with varying camera angles or scene changes. This challenge can render failures such as instance identity forgetting and key frame negligence. In this work, we first attribute the challenge to the lack of multi-shot annotations among existing datasets and therefore we introduce a new dataset termed MultiClip-Bench, featuring dense descriptions and instruction-based question-answering pairs tailored for multi-shot scenarios. We empirically find that the training set significantly boosts the multi-shot performance, while the testing benchmark provides a reliable measure of the model capability in multi-shot scenarios. By further analyzing and discovering that current models only encode instance features in a discrete or lossy manner, at the risk of missing identity information, we then contribute a new model IPFormer-VideoLLM. Its key idea is the injection of instance-level features as instance prompts through an efficient attention-based connector. This allows for the aggregation of instance-specific information across scenes. Experiments demonstrate that our proposed dataset and model not only enhance the multi-scene video understanding significantly, but also offer distinct advantages across various video benchmarks.
Authors: Zipei Ma, Junzhe Jiang, Yurui Chen, Li Zhang
Abstract: The realistic reconstruction of street scenes is critical for developing real-world simulators in autonomous driving. Most existing methods rely on object pose annotations, using these poses to reconstruct dynamic objects and move them during the rendering process. This dependence on high-precision object annotations limits large-scale and extensive scene reconstruction. To address this challenge, we propose B\'ezier curve Gaussian splatting (B\'ezierGS), which represents the motion trajectories of dynamic objects using learnable B\'ezier curves. This approach fully leverages the temporal information of dynamic objects and, through learnable curve modeling, automatically corrects pose errors. By introducing additional supervision on dynamic object rendering and inter-curve consistency constraints, we achieve reasonable and accurate separation and reconstruction of scene elements. Extensive experiments on the Waymo Open Dataset and the nuPlan benchmark demonstrate that B\'ezierGS outperforms state-of-the-art alternatives in both dynamic and static scene components reconstruction and novel view synthesis.
Authors: Hongxing Peng, Lide Chen, Hui Zhu, Yan Chen
Abstract: Unmanned Aerial Vehicle-based Object Detection (UAV-OD) faces substantial challenges, including small target sizes, high-density distributions, and cluttered backgrounds in UAV imagery. Current algorithms often depend on hand-crafted components like anchor boxes, which demand fine-tuning and exhibit limited generalization, and Non-Maximum Suppression (NMS), which is threshold-sensitive and prone to misclassifying dense objects. These generic architectures thus struggle to adapt to aerial imaging characteristics, resulting in performance limitations. Moreover, emerging end-to-end frameworks have yet to effectively mitigate these aerial-specific challenges.To address these issues, we propose HEGS-DETR, a comprehensively enhanced, real-time Detection Transformer framework tailored for UAVs. First, we introduce the High-Frequency Enhanced Semantics Network (HFESNet) as a novel backbone. HFESNet preserves critical high-frequency spatial details to extract robust semantic features, thereby improving discriminative capability for small and occluded targets in complex backgrounds. Second, our Efficient Small Object Pyramid (ESOP) strategy strategically fuses high-resolution feature maps with minimal computational overhead, significantly boosting small object detection. Finally, the proposed Selective Query Recollection (SQR) and Geometry-Aware Positional Encoding (GAPE) modules enhance the detector's decoder stability and localization accuracy, effectively optimizing bounding boxes and providing explicit spatial priors for dense scenes. Experiments on the VisDrone dataset demonstrate that HEGS-DETR achieves a 5.1% AP50 and 3.8% AP increase over the baseline, while maintaining real-time speed and reducing parameter count by 4M.
Authors: Enrico Cassano, Riccardo Renzulli, Andrea Bragagnolo, Marco Grangetto
Abstract: Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key dimensions: (i) interpretability, (ii) unsupervised object discovery, and (iii) alignment with human perception. We first analyze different vision network architectures to examine how varying sparsity levels affect feature attribution interpretability methods. Additionally, we explore whether pruning promotes more succinct and structured representations, potentially improving unsupervised object discovery by discarding redundant information while preserving essential features. Finally, we assess whether pruning enhances the alignment between model representations and human perception, investigating whether sparser models focus on more discriminative features similarly to humans. Our findings also reveal the presence of sweet spots, where sparse models exhibit higher interpretability, downstream generalization and human alignment. However, these spots highly depend on the network architectures and their size in terms of trainable parameters. Our results suggest a complex interplay between these three dimensions, highlighting the importance of investigating when and how pruning benefits vision representations.
Authors: Guiqiu Liao, Matjaz Jogan, Marcel Hussing, Edward Zhang, Eric Eaton, Daniel A. Hashimoto
Abstract: Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasoning about objects and events at a low computational cost and is thus applicable to critical healthcare applications, such as real-time interpretation of surgical video. The heterogeneous scenes in real-world applications like surgery are, however, difficult to parse into a meaningful set of slots. Current approaches with an adaptive slot count perform well on images, but their performance on surgical videos is low. To address this challenge, we propose a dynamic temporal slot transformer (DTST) module that is trained both for temporal reasoning and for predicting the optimal future slot initialization. The model achieves state-of-the-art performance on multiple surgical databases, demonstrating that unsupervised object-centric methods can be applied to real-world data and become part of the common arsenal in healthcare applications.
Authors: Anlin Zheng, Haochen Wang, Yucheng Zhao, Weipeng Deng, Tiancai Wang, Xiangyu Zhang, Xiaojuan Qi
Abstract: Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent tokens, global information is limited. To address this, we introduce \textit{Hita}, a novel image tokenizer for autoregressive (AR) image generation. It introduces a holistic-to-local tokenization scheme with learnable holistic queries and local patch tokens. Hita incorporates two key strategies to better align with the AR generation process: 1) {arranging} a sequential structure with holistic tokens at the beginning, followed by patch-level tokens, and using causal attention to maintain awareness of previous tokens; and 2) adopting a lightweight fusion module before feeding the de-quantized tokens into the decoder to control information flow and prioritize holistic tokens. Extensive experiments show that Hita accelerates the training speed of AR generators and outperforms those trained with vanilla tokenizers, achieving \textbf{2.59 FID} and \textbf{281.9 IS} on the ImageNet benchmark. Detailed analysis of the holistic representation highlights its ability to capture global image properties, such as textures, materials, and shapes. Additionally, Hita also demonstrates effectiveness in zero-shot style transfer and image in-painting. The code is available at \href{https://github.com/CVMI-Lab/Hita}{https://github.com/CVMI-Lab/Hita}.
URLs: https://github.com/CVMI-Lab/Hita, https://github.com/CVMI-Lab/Hita
Authors: Byung Hyun Lee, Wongi Jeong, Woojae Han, Kyoungbun Lee, Se Young Chun
Abstract: Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). However, its adaptability to continual tasks with minimal forgetting has been rarely explored, especially on instance classification for localization. Weakly incremental learning for semantic segmentation has been studied for continual localization, but it focused on natural images, leveraging global relationships among hundreds of small patches (e.g., $16 \times 16$) using pre-trained models. This approach seems infeasible for MIL localization due to enormous amounts ($\sim 10^5$) of large patches (e.g., $256 \times 256$) and no available global relationships such as cancer cells. To address these challenges, we propose Continual Multiple Instance Learning with Enhanced Localization (CoMEL), an MIL framework for both localization and adaptability with minimal forgetting. CoMEL consists of (1) Grouped Double Attention Transformer (GDAT) for efficient instance encoding, (2) Bag Prototypes-based Pseudo-Labeling (BPPL) for reliable instance pseudo-labeling, and (3) Orthogonal Weighted Low-Rank Adaptation (OWLoRA) to mitigate forgetting in both bag and instance classification. Extensive experiments on three public WSI datasets demonstrate superior performance of CoMEL, outperforming the prior arts by up to $11.00\%$ in bag-level accuracy and up to $23.4\%$ in localization accuracy under the continual MIL setup.
Authors: Liheng Zhang, Lexi Pang, Hang Ye, Xiaoxuan Ma, Yizhou Wang
Abstract: Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts. Recent efforts extend these models to incorporate conditional images (e.g., depth or pose maps) for fine-grained spatial control. Among them, feature injection methods have emerged as a training-free alternative to traditional fine-tuning approaches. However, they often suffer from structural misalignment, condition leakage, and visual artifacts, especially when the condition image diverges significantly from natural RGB distributions. By revisiting existing methods, we identify a core limitation: the synchronous injection of condition features fails to account for the trade-off between domain alignment and structural preservation during denoising. Inspired by this observation, we propose a flexible feature injection framework that decouples the injection timestep from the denoising process. At its core is a structure-rich injection module, which enables the model to better adapt to the evolving interplay between alignment and structure preservation throughout the diffusion steps, resulting in more faithful structural generation. In addition, we introduce appearance-rich prompting and a restart refinement strategy to further enhance appearance control and visual quality. Together, these designs enable training-free generation that is both structure-rich and appearance-rich. Extensive experiments show that our approach achieves state-of-the-art performance across diverse zero-shot conditioning scenarios.
Authors: Gent Serifi, Marcel C. B\"uhler
Abstract: We introduce HyperGaussians, a novel extension of 3D Gaussian Splatting for high-quality animatable face avatars. Creating such detailed face avatars from videos is a challenging problem and has numerous applications in augmented and virtual reality. While tremendous successes have been achieved for static faces, animatable avatars from monocular videos still fall in the uncanny valley. The de facto standard, 3D Gaussian Splatting (3DGS), represents a face through a collection of 3D Gaussian primitives. 3DGS excels at rendering static faces, but the state-of-the-art still struggles with nonlinear deformations, complex lighting effects, and fine details. While most related works focus on predicting better Gaussian parameters from expression codes, we rethink the 3D Gaussian representation itself and how to make it more expressive. Our insights lead to a novel extension of 3D Gaussians to high-dimensional multivariate Gaussians, dubbed 'HyperGaussians'. The higher dimensionality increases expressivity through conditioning on a learnable local embedding. However, splatting HyperGaussians is computationally expensive because it requires inverting a high-dimensional covariance matrix. We solve this by reparameterizing the covariance matrix, dubbed the 'inverse covariance trick'. This trick boosts the efficiency so that HyperGaussians can be seamlessly integrated into existing models. To demonstrate this, we plug in HyperGaussians into the state-of-the-art in fast monocular face avatars: FlashAvatar. Our evaluation on 19 subjects from 4 face datasets shows that HyperGaussians outperform 3DGS numerically and visually, particularly for high-frequency details like eyeglass frames, teeth, complex facial movements, and specular reflections.
Authors: Guang Yang
Abstract: The rapid advancement of diffusion models, particularly Stable Diffusion 3.5, has enabled the generation of highly photorealistic synthetic images that pose significant challenges to existing detection methods. This paper presents FreqCross, a novel multi-modal fusion network that combines spatial RGB features, frequency domain artifacts, and radial energy distribution patterns to achieve robust detection of AI-generated images. Our approach leverages a three-branch architecture: (1) a ResNet-18 backbone for spatial feature extraction, (2) a lightweight CNN for processing 2D FFT magnitude spectra, and (3) a multi-layer perceptron for analyzing radial energy profiles. We introduce a novel radial energy distribution analysis that captures characteristic frequency artifacts inherent in diffusion-generated images, and fuse it with spatial and spectral cues via simple feature concatenation followed by a compact classification head. Extensive experiments on a dataset of 10,000 paired real (MS-COCO) and synthetic (Stable Diffusion 3.5) images demonstrate that FreqCross achieves 97.8\% accuracy, outperforming state-of-the-art baselines by 5.2\%. The frequency analysis further reveals that synthetic images exhibit distinct spectral signatures in the 0.1--0.4 normalised frequency range, providing theoretical foundation for our approach. Code and pre-trained models are publicly available to facilitate reproducible research.
Authors: Jerome Luescher, Nora Koreuber, Jannik Franzen, Fabian H. Reith, Claudia Winklmayr, Elias Baumann, Christian M. Schuerch, Dagmar Kainmueller, Josef Lorenz Rumberger
Abstract: Digital pathology has seen the advent of a wealth of foundational models (FM), yet to date their performance on cell phenotyping has not been benchmarked in a unified manner. We therefore propose PhenoBench: A comprehensive benchmark for cell phenotyping on Hematoxylin and Eosin (H&E) stained histopathology images. We provide both PhenoCell, a new H&E dataset featuring 14 granular cell types identified by using multiplexed imaging, and ready-to-use fine-tuning and benchmarking code that allows the systematic evaluation of multiple prominent pathology FMs in terms of dense cell phenotype predictions in different generalization scenarios. We perform extensive benchmarking of existing FMs, providing insights into their generalization behavior under technical vs. medical domain shifts. Furthermore, while FMs achieve macro F1 scores > 0.70 on previously established benchmarks such as Lizard and PanNuke, on PhenoCell, we observe scores as low as 0.20. This indicates a much more challenging task not captured by previous benchmarks, establishing PhenoCell as a prime asset for future benchmarking of FMs and supervised models alike. Code and data are available on GitHub.
Authors: Amirabbas Hojjati, Lu Li, Ibrahim Hameed, Anis Yazidi, Pedro G. Lind, Rabindra Khadka
Abstract: EEG signals capture brain activity with high temporal and low spatial resolution, supporting applications such as neurological diagnosis, cognitive monitoring, and brain-computer interfaces. However, effective analysis is hindered by limited labeled data, high dimensionality, and the absence of scalable models that fully capture spatiotemporal dependencies. Existing self-supervised learning (SSL) methods often focus on either spatial or temporal features, leading to suboptimal representations. To this end, we propose EEG-VJEPA, a novel adaptation of the Video Joint Embedding Predictive Architecture (V-JEPA) for EEG classification. By treating EEG as video-like sequences, EEG-VJEPA learns semantically meaningful spatiotemporal representations using joint embeddings and adaptive masking. To our knowledge, this is the first work that exploits V-JEPA for EEG classification and explores the visual concepts learned by the model. Evaluations on the publicly available Temple University Hospital (TUH) Abnormal EEG dataset show that EEG-VJEPA outperforms existing state-of-the-art models in classification accuracy. Beyond classification accuracy, EEG-VJEPA captures physiologically relevant spatial and temporal signal patterns, offering interpretable embeddings that may support human-AI collaboration in diagnostic workflows. These findings position EEG-VJEPA as a promising framework for scalable, trustworthy EEG analysis in real-world clinical settings.
Authors: Akio Kodaira, Tingbo Hou, Ji Hou, Masayoshi Tomizuka, Yue Zhao
Abstract: Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-quality videos. However, existing models typically produce only short clips offline, restricting their use cases in interactive and real-time applications. This paper addresses these challenges by proposing StreamDiT, a streaming video generation model. StreamDiT training is based on flow matching by adding a moving buffer. We design mixed training with different partitioning schemes of buffered frames to boost both content consistency and visual quality. StreamDiT modeling is based on adaLN DiT with varying time embedding and window attention. To practice the proposed method, we train a StreamDiT model with 4B parameters. In addition, we propose a multistep distillation method tailored for StreamDiT. Sampling distillation is performed in each segment of a chosen partitioning scheme. After distillation, the total number of function evaluations (NFEs) is reduced to the number of chunks in a buffer. Finally, our distilled model reaches real-time performance at 16 FPS on one GPU, which can generate video streams at 512p resolution. We evaluate our method through both quantitative metrics and human evaluation. Our model enables real-time applications, e.g. streaming generation, interactive generation, and video-to-video. We provide video results and more examples in our project website: https://cumulo-autumn.github.io/StreamDiT/
Authors: Aleksandr Gushchin, Maksim Smirnov, Dmitriy Vatolin, Anastasia Antsiferova
Abstract: We propose the LEHA-CVQAD (Large-scale Enriched Human-Annotated Compressed Video Quality Assessment) dataset, which comprises 6,240 clips for compression-oriented video quality assessment. 59 source videos are encoded with 186 codec-preset variants, 1.8M pairwise, and 1.5k MOS ratings are fused into a single quality scale; part of the videos remains hidden for blind evaluation. We also propose Rate-Distortion Alignment Error (RDAE), a novel evaluation metric that quantifies how well VQA models preserve bitrate-quality ordering, directly supporting codec parameter tuning. Testing IQA/VQA methods reveals that popular VQA metrics exhibit high RDAE and lower correlations, underscoring the dataset challenges and utility. The open part and the results of LEHA-CVQAD are available at https://aleksandrgushchin.github.io/lcvqad/
Authors: Xinbo Wang, Wenju Xu, Qing Zhang, Wei-Shi Zheng
Abstract: This paper presents a portrait style transfer method that generalizes well to various different domains while enabling high-quality semantic-aligned stylization on regions including hair, eyes, eyelashes, skins, lips, and background. To this end, we propose to establish dense semantic correspondence between the given input and reference portraits based on a pre-trained model and a semantic adapter, with which we obtain a warped reference semantically aligned with the input. To ensure effective yet controllable style transfer, we devise an AdaIN-Wavelet transform to balance content preservation and stylization by blending low-frequency information of the warped reference with high-frequency information of the input in the latent space. A style adapter is also designed to provide style guidance from the warped reference. With the stylized latent from AdaIN-Wavelet transform, we employ a dual-conditional diffusion model that integrates a ControlNet recording high-frequency information and the style guidance to generate the final result. Extensive experiments demonstrate the superiority of our method. Our code and trained model are available at https://github.com/wangxb29/DGPST.
Authors: Xinhua Lu, Runhe Lai, Yanqi Wu, Kanghao Chen, Wei-Shi Zheng, Ruixuan Wang
Abstract: Pre-trained vision-language models (VLMs) have advanced out-of-distribution (OOD) detection recently. However, existing CLIP-based methods often focus on learning OOD-related knowledge to improve OOD detection, showing limited generalization or reliance on external large-scale auxiliary datasets. In this study, instead of delving into the intricate OOD-related knowledge, we propose an innovative CLIP-based framework based on Forced prompt leArning (FA), designed to make full use of the In-Distribution (ID) knowledge and ultimately boost the effectiveness of OOD detection. Our key insight is to learn a prompt (i.e., forced prompt) that contains more diversified and richer descriptions of the ID classes beyond the textual semantics of class labels. Specifically, it promotes better discernment for ID images, by forcing more notable semantic similarity between ID images and the learnable forced prompt. Moreover, we introduce a forced coefficient, encouraging the forced prompt to learn more comprehensive and nuanced descriptions of the ID classes. In this way, FA is capable of achieving notable improvements in OOD detection, even when trained without any external auxiliary datasets, while maintaining an identical number of trainable parameters as CoOp. Extensive empirical evaluations confirm our method consistently outperforms current state-of-the-art methods. Code is available at https://github.com/0xFAFA/FA.
Authors: Xixi Wan, Aihua Zheng, Bo Jiang, Beibei Wang, Chenglong Li, Jin Tang
Abstract: Multi-modal object Re-IDentification (ReID) has gained considerable attention with the goal of retrieving specific targets across cameras using heterogeneous visual data sources. Existing methods primarily aim to improve identification performance, but often overlook the uncertainty arising from inherent defects, such as intra-modal noise and inter-modal conflicts. This uncertainty is particularly significant in the case of fine-grained local occlusion and frame loss, which becomes a challenge in multi-modal learning. To address the above challenge, we propose a robust approach named Uncertainty-Guided Graph model for multi-modal object ReID (UGG-ReID). UGG-ReID is designed to mitigate noise interference and facilitate effective multi-modal fusion by estimating both local and sample-level aleatoric uncertainty and explicitly modeling their dependencies. Specifically, we first propose the Gaussian patch-graph representation model that leverages uncertainty to quantify fine-grained local cues and capture their structural relationships. This process boosts the expressiveness of modal-specific information, ensuring that the generated embeddings are both more informative and robust. Subsequently, we design an uncertainty-guided mixture of experts strategy that dynamically routes samples to experts exhibiting low uncertainty. This strategy effectively suppresses noise-induced instability, leading to enhanced robustness. Meanwhile, we design an uncertainty-guided routing to strengthen the multi-modal interaction, improving the performance. UGG-ReID is comprehensively evaluated on five representative multi-modal object ReID datasets, encompassing diverse spectral modalities. Experimental results show that the proposed method achieves excellent performance on all datasets and is significantly better than current methods in terms of noise immunity. Our code will be made public upon acceptance.
Authors: Hahyeon Choi, Junhoo Lee, Nojun Kwak
Abstract: Audio-Visual Localization (AVL) aims to identify sound-emitting sources within a visual scene. However, existing studies focus on image-level audio-visual associations, failing to capture temporal dynamics. Moreover, they assume simplified scenarios where sound sources are always visible and involve only a single object. To address these limitations, we propose AVATAR, a video-centric AVL benchmark that incorporates high-resolution temporal information. AVATAR introduces four distinct scenarios -- Single-sound, Mixed-sound, Multi-entity, and Off-screen -- enabling a more comprehensive evaluation of AVL models. Additionally, we present TAVLO, a novel video-centric AVL model that explicitly integrates temporal information. Experimental results show that conventional methods struggle to track temporal variations due to their reliance on global audio features and frame-level mappings. In contrast, TAVLO achieves robust and precise audio-visual alignment by leveraging high-resolution temporal modeling. Our work empirically demonstrates the importance of temporal dynamics in AVL and establishes a new standard for video-centric audio-visual localization.
Authors: Abiao Li, Chenlei Lv, Yuming Fang, Yifan Zuo, Jian Zhang, Guofeng Mei
Abstract: Most masked point cloud modeling (MPM) methods follow a regression paradigm to reconstruct the coordinate or feature of masked regions. However, they tend to over-constrain the model to learn the details of the masked region, resulting in failure to capture generalized features. To address this limitation, we propose \textbf{\textit{PointGAC}}, a novel clustering-based MPM method that aims to align the feature distribution of masked regions. Specially, it features an online codebook-guided teacher-student framework. Firstly, it presents a geometry-aware partitioning strategy to extract initial patches. Then, the teacher model updates a codebook via online k-means based on features extracted from the complete patches. This procedure facilitates codebook vectors to become cluster centers. Afterward, we assigns the unmasked features to their corresponding cluster centers, and the student model aligns the assignment for the reconstructed masked features. This strategy focuses on identifying the cluster centers to which the masked features belong, enabling the model to learn more generalized feature representations. Benefiting from a proposed codebook maintenance mechanism, codebook vectors are actively updated, which further increases the efficiency of semantic feature learning. Experiments validate the effectiveness of the proposed method on various downstream tasks. Code is available at https://github.com/LAB123-tech/PointGAC
Authors: Samuel Barbeau, Pedram Fekri, David Osowiechi, Ali Bahri, Moslem Yazdanpanah, Masih Aminbeidokhti, Christian Desrosiers
Abstract: Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes. Test-Time Training (TTT) has emerged as an effective method to enhance model robustness by incorporating an auxiliary unsupervised task during training and leveraging it for model updates at test time. In this work, we introduce CTA (Cross-Task Alignment), a novel approach for improving TTT. Unlike existing TTT methods, CTA does not require a specialized model architecture and instead takes inspiration from the success of multi-modal contrastive learning to align a supervised encoder with a self-supervised one. This process enforces alignment between the learned representations of both models, thereby mitigating the risk of gradient interference, preserving the intrinsic robustness of self-supervised learning and enabling more semantically meaningful updates at test-time. Experimental results demonstrate substantial improvements in robustness and generalization over the state-of-the-art on several benchmark datasets.
Authors: Milena Gazdieva, Petr Mokrov, Litu Rout, Alexander Korotin, Andrey Kravchenko, Alexander Filippov, Evgeny Burnaev
Abstract: Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached by unpaired techniques based on Generative Adversarial Networks (GANs), which yield complex training losses with several regularization terms, e.g., content or identity losses. While GANs usually provide good practical performance, they are used heuristically, i.e., theoretical understanding of their behaviour is yet rather limited. We theoretically investigate optimization problems which arise in such models and find two surprising observations. First, the learned SR map is always an optimal transport (OT) map. Second, we theoretically prove and empirically show that the learned map is biased, i.e., it does not actually transform the distribution of low-resolution images to high-resolution ones. Inspired by these findings, we investigate recent advances in neural OT field to resolve the bias issue. We establish an intriguing connection between regularized GANs and neural OT approaches. We show that unlike the existing GAN-based alternatives, these algorithms aim to learn an unbiased OT map. We empirically demonstrate our findings via a series of synthetic and real-world unpaired SR experiments. Our source code is publicly available at https://github.com/milenagazdieva/OT-Super-Resolution.
URLs: https://github.com/milenagazdieva/OT-Super-Resolution.
Authors: Chongyu Qu, Tiezheng Zhang, Hualin Qiao, Jie Liu, Yucheng Tang, Alan Yuille, Zongwei Zhou
Abstract: Annotating medical images, particularly for organ segmentation, is laborious and time-consuming. For example, annotating an abdominal organ requires an estimated rate of 30-60 minutes per CT volume based on the expertise of an annotator and the size, visibility, and complexity of the organ. Therefore, publicly available datasets for multi-organ segmentation are often limited in data size and organ diversity. This paper proposes an active learning method to expedite the annotation process for organ segmentation and creates the largest multi-organ dataset (by far) with the spleen, liver, kidneys, stomach, gallbladder, pancreas, aorta, and IVC annotated in 8,448 CT volumes, equating to 3.2 million slices. The conventional annotation methods would take an experienced annotator up to 1,600 weeks (or roughly 30.8 years) to complete this task. In contrast, our annotation method has accomplished this task in three weeks (based on an 8-hour workday, five days a week) while maintaining a similar or even better annotation quality. This achievement is attributed to three unique properties of our method: (1) label bias reduction using multiple pre-trained segmentation models, (2) effective error detection in the model predictions, and (3) attention guidance for annotators to make corrections on the most salient errors. Furthermore, we summarize the taxonomy of common errors made by AI algorithms and annotators. This allows for continuous revision of both AI and annotations and significantly reduces the annotation costs required to create large-scale datasets for a wider variety of medical imaging tasks.
Authors: Alistair Weld, Luke Dixon, Giulio Anichini, Michael Dyck, Alex Ranne, Sophie Camp, Stamatia Giannarou
Abstract: Purpose: Intraoperative ultrasound scanning is a demanding visuotactile task. It requires operators to simultaneously localise the ultrasound perspective and manually perform slight adjustments to the pose of the probe, making sure not to apply excessive force or breaking contact with the tissue, whilst also characterising the visible tissue. Method: To analyse the probe-tissue contact, an iterative filtering and topological method is proposed to identify the underlying visible tissue, which can be used to detect acoustic shadow and construct confidence maps of perceptual salience. Results: For evaluation, datasets containing both in vivo and medical phantom data are created. A suite of evaluations is performed, including an evaluation of acoustic shadow classification. Compared to an ablation, deep learning, and statistical method, the proposed approach achieves superior classification on in vivo data, achieving an F_beta score of 0.864, in comparison to 0.838, 0.808, 0.808. A novel framework for evaluating the confidence estimation of probe tissue contact is created. The phantom data is captured specifically for this, and comparison is made against two established methods. The proposed method produced the superior response, achieving an average normalised root mean square error of 0.168, in comparison to 1.836 and 4.542. Evaluation is also extended to determine the algorithm's robustness to parameter perturbation, speckle noise, data distribution shift, and capability for guiding a robotic scan. Conclusion: The results of this comprehensive set of experiments justify the potential clinical value of the proposed algorithm, which can be used to support clinical training and robotic ultrasound automation.
Authors: Pallabi Dutta, Soham Bose, Swalpa Kumar Roy, Sushmita Mitra
Abstract: The development of efficient segmentation strategies for medical images has evolved from its initial dependence on Convolutional Neural Networks (CNNs) to the current investigation of hybrid models that combine CNNs with Vision Transformers (ViTs). There is an increasing focus on creating architectures that are both high-performing and computationally efficient, capable of being deployed on remote systems with limited resources. Although transformers can capture global dependencies in the input space, they face challenges from the corresponding high computational and storage expenses involved. This research investigates the integration of CNNs with Vision Extended Long Short-Term Memory (Vision-xLSTM)s by introducing the novel U-VixLSTM. The Vision-xLSTM blocks capture the temporal and global relationships within the patches extracted from the CNN feature maps. The convolutional feature reconstruction path upsamples the output volume from the Vision-xLSTM blocks to produce the segmentation output. Our primary objective is to propose that Vision-xLSTM forms an appropriate backbone for medical image segmentation, offering excellent performance with reduced computational costs. The U-VixLSTM exhibits superior performance compared to the state-of-the-art networks in the publicly available Synapse, ISIC and ACDC datasets. Code provided: https://github.com/duttapallabi2907/U-VixLSTM
Authors: Kento Tomita, Koki Ho
Abstract: Onboard terrain sensing and mapping for safe planetary landings often suffer from missed hazardous features, e.g., small rocks, due to the large observational range and the limited resolution of the obtained terrain data. To this end, this paper develops a novel real-time stochastic terrain mapping algorithm that accounts for topographic uncertainty between the sampled points, or the uncertainty due to the sparse 3D terrain measurements. We introduce a Gaussian digital elevation map that is efficiently constructed using the combination of Delauney triangulation and local Gaussian process regression. The geometric investigation of the lander-terrain interaction is exploited to efficiently evaluate the marginally conservative local slope and roughness while avoiding the costly computation of the local plane. The conservativeness is proved in the paper. The developed real-time uncertainty quantification pipeline enables stochastic landing safety evaluation under challenging operational conditions, such as a large observational range or limited sensor capability, which is a critical stepping stone for the development of predictive guidance algorithms for safe autonomous planetary landing. Detailed reviews on background and related works are also presented.
Authors: Bilal Kabas, Fuat Arslan, Valiyeh A. Nezhad, Saban Ozturk, Emine U. Saritas, Tolga \c{C}ukur
Abstract: Medical image reconstruction from undersampled acquisitions is an ill-posed problem involving inversion of the imaging operator linking measurement and image domains. Physics-driven (PD) models have gained prominence in reconstruction tasks due to their desirable performance and generalization. These models jointly promote data fidelity and artifact suppression, typically by combining data-consistency mechanisms with learned network modules. Artifact suppression depends on the network's ability to disentangle artifacts from true tissue signals, both of which can exhibit contextual structure across diverse spatial scales. Convolutional neural networks (CNNs) are strong in capturing local correlations, albeit relatively insensitive to non-local context. While transformers promise to alleviate this limitation, practical implementations frequently involve design compromises to reduce computational cost by balancing local and non-local sensitivity, occasionally resulting in performance comparable to or trailing that of CNNs. To enhance contextual sensitivity without incurring high complexity, we introduce a novel physics-driven autoregressive state-space model (MambaRoll) for medical image reconstruction. In each cascade of its unrolled architecture, MambaRoll employs a physics-driven state-space module (PD-SSM) to aggregate contextual features efficiently at a given spatial scale, and autoregressively predicts finer-scale feature maps conditioned on coarser-scale features to capture multi-scale context. Learning across scales is further enhanced via a deep multi-scale decoding (DMSD) loss tailored to the autoregressive prediction task. Demonstrations on accelerated MRI and sparse-view CT reconstructions show that MambaRoll consistently outperforms state-of-the-art data-driven and physics-driven methods based on CNN, transformer, and SSM backbones.
Authors: Bailiang Jian, Jiazhen Pan, Yitong Li, Fabian Bongratz, Ruochen Li, Daniel Rueckert, Benedikt Wiestler, Christian Wachinger
Abstract: Predicting future brain states is crucial for understanding healthy aging and neurodegenerative diseases. Longitudinal brain MRI registration, a cornerstone for such analyses, has long been limited by its inability to forecast future developments, reliance on extensive dense longitudinal data, and the need to balance registration accuracy with temporal smoothness. In this work, we present \emph{TimeFlow}, a novel framework for longitudinal brain MRI registration that overcomes all these challenges. TimeFlow leverages a U-Net architecture with temporal conditioning inspired by diffusion models, enabling accurate registration using only two images as input and facilitating prospective analyses through future image prediction. Unlike traditional methods, TimeFlow eliminates the demand for explicit smoothness regularizers and dense sequential data while maintaining temporal consistency and continuity. Experimental results highlight its superior performance in both future timepoint prediction and registration accuracy compared to state-of-the-art methods. Additionally, TimeFlow supports novel biological brain aging analyses, effectively differentiating neurodegenerative conditions from healthy aging, all without requiring segmentation, thus avoiding non-trivial annotation and inconsistent segmentation flaws. This framework paves the way for accurate, data-efficient, and annotation-free prospective analyses of brain aging and chronic diseases.
Authors: Jianzhou Chen, Jinyang Sun, Xiumei Wang, Xi Chen, Heyu Chu, Guo Song, Yuji Luo, Xingping Zhou, Rong Gu
Abstract: Heart failure is one of the leading causes of death worldwide, with millons of deaths each year, according to data from the World Health Organization (WHO) and other public health agencies. While significant progress has been made in the field of heart failure, leading to improved survival rates and improvement of ejection fraction, there remains substantial unmet needs, due to the complexity and multifactorial characteristics. Therefore, we propose a composable strategy framework for assessment and treatment optimization in heart failure. This framework simulates the doctor-patient consultation process and leverages multi-modal algorithms to analyze a range of data, including video, physical examination, text results as well as medical history. By integrating these various data sources, our framework offers a more holistic evaluation and optimized treatment plan for patients. Our results demonstrate that this multi-modal approach outperforms single-modal artificial intelligence (AI) algorithms in terms of accuracy in heart failure (HF) prognosis prediction. Through this method, we can further evaluate the impact of various pathological indicators on HF prognosis,providing a more comprehensive evaluation.
Authors: Pengcheng Zheng, Kecheng Chen, Jiaxin Huang, Bohao Chen, Ju Liu, Yazhou Ren, Xiaorong Pu
Abstract: Medical image restoration tasks aim to recover high-quality images from degraded observations, exhibiting emergent desires in many clinical scenarios, such as low-dose CT image denoising, MRI super-resolution, and MRI artifact removal. Despite the success achieved by existing deep learning-based restoration methods with sophisticated modules, they struggle with rendering computationally-efficient reconstruction results. Moreover, they usually ignore the reliability of the restoration results, which is much more urgent in medical systems. To alleviate these issues, we present LRformer, a Lightweight Transformer-based method via Reliability-guided learning in the frequency domain. Specifically, inspired by the uncertainty quantification in Bayesian neural networks (BNNs), we develop a Reliable Lesion-Semantic Prior Producer (RLPP). RLPP leverages Monte Carlo (MC) estimators with stochastic sampling operations to generate sufficiently-reliable priors by performing multiple inferences on the foundational medical image segmentation model, MedSAM. Additionally, instead of directly incorporating the priors in the spatial domain, we decompose the cross-attention (CA) mechanism into real symmetric and imaginary anti-symmetric parts via fast Fourier transform (FFT), resulting in the design of the Guided Frequency Cross-Attention (GFCA) solver. By leveraging the conjugated symmetric property of FFT, GFCA reduces the computational complexity of naive CA by nearly half. Extensive experimental results in various tasks demonstrate the superiority of the proposed LRformer in both effectiveness and efficiency.
Authors: Arthur Allshire, Hongsuk Choi, Junyi Zhang, David McAllister, Anthony Zhang, Chung Min Kim, Trevor Darrell, Pieter Abbeel, Jitendra Malik, Angjoo Kanazawa
Abstract: How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and descents, sitting and standing from chairs and benches, as well as other dynamic whole-body skills-all from a single policy, conditioned on the environment and global root commands. VIDEOMIMIC offers a scalable path towards teaching humanoids to operate in diverse real-world environments.
Authors: Pegah Salehi, Sajad Amouei Sheshkal, Vajira Thambawita, Michael A. Riegler, P{\aa}l Halvorsen
Abstract: Dynamic facial emotion is essential for believable AI-generated avatars, yet most systems remain visually static, limiting their use in simulations like virtual training for investigative interviews with abused children. We present a real-time architecture combining Unreal Engine 5 MetaHuman rendering with NVIDIA Omniverse Audio2Face to generate facial expressions from vocal prosody in photorealistic child avatars. Due to limited TTS options, both avatars were voiced using young adult female models from two systems to better fit character profiles, introducing a voice-age mismatch. This confound may affect audiovisual alignment. We used a two-PC setup to decouple speech generation from GPU-intensive rendering, enabling low-latency interaction in desktop and VR. A between-subjects study (N=70) compared audio+visual vs. visual-only conditions as participants rated emotional clarity, facial realism, and empathy for avatars expressing joy, sadness, and anger. While emotions were generally recognized - especially sadness and joy - anger was harder to detect without audio, highlighting the role of voice in high-arousal expressions. Interestingly, silencing clips improved perceived realism by removing mismatches between voice and animation, especially when tone or age felt incongruent. These results emphasize the importance of audiovisual congruence: mismatched voice undermines expression, while a good match can enhance weaker visuals - posing challenges for emotionally coherent avatars in sensitive contexts.
Authors: Fengyi Jiang, Xiaorui Zhang, Lingbo Jin, Ruixing Liang, Yuxin Chen, Adi Chola Venkatesh, Jason Culman, Tiantian Wu, Lirong Shao, Wenqing Sun, Cong Gao, Hallie McNamara, Jingpei Lu, Omid Mohareri
Abstract: High-resolution imaging is crucial for enhancing visual clarity and enabling precise computer-assisted guidance in minimally invasive surgery (MIS). Despite the increasing adoption of 4K endoscopic systems, there remains a significant gap in publicly available native 4K datasets tailored specifically for robotic-assisted MIS. We introduce SurgiSR4K, the first publicly accessible surgical imaging and video dataset captured at a native 4K resolution, representing realistic conditions of robotic-assisted procedures. SurgiSR4K comprises diverse visual scenarios including specular reflections, tool occlusions, bleeding, and soft tissue deformations, meticulously designed to reflect common challenges faced during laparoscopic and robotic surgeries. This dataset opens up possibilities for a broad range of computer vision tasks that might benefit from high resolution data, such as super resolution (SR), smoke removal, surgical instrument detection, 3D tissue reconstruction, monocular depth estimation, instance segmentation, novel view synthesis, and vision-language model (VLM) development. SurgiSR4K provides a robust foundation for advancing research in high-resolution surgical imaging and fosters the development of intelligent imaging technologies aimed at enhancing performance, safety, and usability in image-guided robotic surgeries.
Authors: Yi Zhang, Yidong Zhao, Qian Tao
Abstract: Deformable medical image registration is traditionally formulated as an optimization problem. While classical methods solve this problem iteratively, recent learning-based approaches use recurrent neural networks (RNNs) to mimic this process by unrolling the prediction of deformation fields in a fixed number of steps. However, classical methods typically converge after sufficient iterations, but learning-based unrolling methods lack a theoretical convergence guarantee and show instability empirically. In addition, unrolling methods have a practical bottleneck at training time: GPU memory usage grows linearly with the unrolling steps due to backpropagation through time (BPTT). To address both theoretical and practical challenges, we propose DEQReg, a novel registration framework based on Deep Equilibrium Models (DEQ), which formulates registration as an equilibrium-seeking problem, establishing a natural connection between classical optimization and learning-based unrolling methods. DEQReg maintains constant memory usage, enabling theoretically unlimited iteration steps. Through extensive evaluation on the public brain MRI and lung CT datasets, we show that DEQReg can achieve competitive registration performance, while substantially reducing memory consumption compared to state-of-the-art unrolling methods. We also reveal an intriguing phenomenon: the performance of existing unrolling methods first increases slightly then degrades irreversibly when the inference steps go beyond the training configuration. In contrast, DEQReg achieves stable convergence with its inbuilt equilibrium-seeking mechanism, bridging the gap between classical optimization-based and modern learning-based registration methods.
Authors: Hyoseo (Lauren), Yoon, Yisong Yue, Been Kim
Abstract: Independently trained vision and language models inhabit disjoint representational spaces, shaped by their respective modalities, objectives, and architectures. Yet an emerging hypothesis - the Platonic Representation Hypothesis - suggests that such models may nonetheless converge toward a shared statistical model of reality. This compatibility, if it exists, raises a fundamental question: can we move beyond post-hoc statistical detection of alignment and explicitly optimize for it between such disjoint representations? We cast this Platonic alignment problem as a multi-objective optimization task - preserve each modality's native structure while aligning for mutual coherence. We introduce the Joint Autoencoder Modulator (JAM) framework that jointly trains modality-specific autoencoders on the latent representations of pre-trained single modality models, encouraging alignment through both reconstruction and cross-modal objectives. By analogy, this framework serves as a method to escape Plato's Cave, enabling the emergence of shared structure from disjoint inputs. We evaluate this framework across three critical design axes: (i) the alignment objective - comparing contrastive loss (Con), its hard-negative variant (NegCon), and our Spread loss, (ii) the layer depth at which alignment is most effective, and (iii) the impact of foundation model scale on representational convergence. Our findings show that our lightweight Pareto-efficient framework reliably induces alignment, even across frozen, independently trained representations, offering both theoretical insight and practical pathways for transforming generalist unimodal foundations into specialist multimodal models.
Authors: Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, C\'ian Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, Lu Yang, Kejia Chen, Per Bjornsson, Shashir Reddy, Ryan Brush, Kenneth Philbrick, Howard Hu, Howard Yang, Richa Tiwari, Sunny Jansen, Preeti Singh, Yun Liu, Shekoofeh Azizi, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ram\'e, Morgane Riviere, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Elena Buchatskaya, Jean-Baptiste Alayrac, Dmitry Lepikhin, Vlad Feinberg, Sebastian Borgeaud, Alek Andreev, Cassidy Hardin, Robert Dadashi, L\'eonard Hussenot, Armand Joulin, Olivier Bachem, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Clement Farabet, Joelle Barral, Tris Warkentin, Jonathon Shlens, David Fleet, Victor Cotruta, Omar Sanseviero, Gus Martins, Phoebe Kirk, Anand Rao, Shravya Shetty, David F. Steiner, Can Kirmizibayrak, Rory Pilgrim, Daniel Golden, Lin Yang
Abstract: Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks, and the need to preserve privacy. Foundation models that perform well on medical tasks and require less task-specific tuning data are critical to accelerate the development of healthcare AI applications. We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B. MedGemma demonstrates advanced medical understanding and reasoning on images and text, significantly exceeding the performance of similar-sized generative models and approaching the performance of task-specific models, while maintaining the general capabilities of the Gemma 3 base models. For out-of-distribution tasks, MedGemma achieves 2.6-10% improvement on medical multimodal question answering, 15.5-18.1% improvement on chest X-ray finding classification, and 10.8% improvement on agentic evaluations compared to the base models. Fine-tuning MedGemma further improves performance in subdomains, reducing errors in electronic health record information retrieval by 50% and reaching comparable performance to existing specialized state-of-the-art methods for pneumothorax classification and histopathology patch classification. We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP. MedSigLIP powers the visual understanding capabilities of MedGemma and as an encoder achieves comparable or better performance than specialized medical image encoders. Taken together, the MedGemma collection provides a strong foundation of medical image and text capabilities, with potential to significantly accelerate medical research and development of downstream applications. The MedGemma collection, including tutorials and model weights, can be found at https://goo.gle/medgemma.