Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Thursday 30 October

Computer Vision

MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models

Accurate estimation of motion information is crucial in diverse computational imaging and computer vision applications. Researchers have investigated various methods to extract motion information from a single blurred image, including blur kernels and optical flow. However, existing motion representations are often of low quality, i.e., coarse-grained and inaccurate. In this paper, we propose the first high-resolution (HR) Motion Trajectory estimation framework using Diffusion models (MoTDiff). Different from existing motion representations, we aim to estimate an HR motion trajectory with high-quality from a single motion-blurred image. The proposed MoTDiff consists of two key components: 1) a new conditional diffusion framework that uses multi-scale feature maps extracted from a single blurred image as a condition, and 2) a new training method that can promote precise identification of a fine-grained motion trajectory, consistent estimation of overall shape and position of a motion path, and pixel connectivity along a motion trajectory. Our experiments demonstrate that the proposed MoTDiff can outperform state-of-the-art methods in both blind image deblurring and coded exposure photography applications.
Read the full abstract

All authors Wontae Choi, Jaelin Lee, Hyung Sup Yun, Byeungwoo Jeon, Il Yong Chun

Computer Vision · Cross-listed from cs.RO

Self-localization on a 3D map by fusing global and local features from a monocular camera

Self-localization on a 3D map by using an inexpensive monocular camera is required to realize autonomous driving. Self-localization based on a camera often uses a convolutional neural network (CNN) that can extract local features that are calculated by nearby pixels. However, when dynamic obstacles, such as people, are present, CNN does not work well. This study proposes a new method combining CNN with Vision Transformer, which excels at extracting global features that show the relationship of patches on whole image. Experimental results showed that, compared to the state-of-the-art method (SOTA), the accuracy improvement rate in a CG dataset with dynamic obstacles is 1.5 times higher than that without dynamic obstacles. Moreover, the self-localization error of our method is 20.1% smaller than that of SOTA on public datasets. Additionally, our robot using our method can localize itself with 7.51cm error on average, which is more accurate than SOTA.
Read the full abstract

Computer Vision

CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark

Wearable devices such as smart glasses are transforming the way people interact with their surroundings, enabling users to seek information regarding entities in their view. Multi-Modal Retrieval-Augmented Generation (MM-RAG) plays a key role in supporting such questions, yet there is still no comprehensive benchmark for this task, especially regarding wearables scenarios. To fill this gap, we present CRAG-MM – a Comprehensive RAG benchmark for Multi-modal Multi-turn conversations. CRAG-MM contains a diverse set of 6.5K (image, question, answer) triplets and 2K visual-based multi-turn conversations across 13 domains, including 6.2K egocentric images designed to mimic captures from wearable devices. We carefully constructed the questions to reflect real-world scenarios and challenges, including five types of image-quality issues, six question types, varying entity popularity, differing information dynamism, and different conversation turns. We design three tasks: single-source augmentation, multi-source augmentation, and multi-turn conversations – each paired with an associated retrieval corpus and APIs for both image-KG retrieval and webpage retrieval. Our evaluation shows that straightforward RAG approaches achieve only 32% and 43% truthfulness on CRAG-MM single- and multi-turn QA, respectively, whereas state-of-the-art industry solutions have similar quality (32%/45%), underscoring ample room for improvement. The benchmark has hosted KDD Cup 2025, attracting about 1K participants and 5K submissions, with winning solutions improving baseline performance by 28%, highlighting its early impact on advancing the field.
Read the full abstract

All authors Jiaqi Wang, Xiao Yang, Kai Sun, Parth Suresh, Sanat Sharma, Adam Czyzewski, Derek Andersen, Surya Appini, Arkav Banerjee, Sajal Choudhary, Shervin Ghasemlou, Ziqiang Guan, Akil Iyer, Haidar Khan, Lingkun Kong, Roy Luo, Tiffany Ma, Zhen Qiao, David Tran, Wenfang Xu, Skyler Yeatman, Chen Zhou, Gunveer Gujral, Yinglong Xia, Shane Moon, Nicolas Scheffer, Nirav Shah, Eun Chang, Yue Liu, Florian Metze, Tammy Stark, Zhaleh Feizollahi, Andrea Jessee, Mangesh Pujari, Ahmed Aly, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, Wen-tau Yih, Xin Luna Dong

Computer Vision

Detecting Unauthorized Vehicles using Deep Learning for Smart Cities: A Case Study on Bangladesh

Modes of transportation vary across countries depending on geographical location and cultural context. In South Asian countries rickshaws are among the most common means of local transport. Based on their mode of operation, rickshaws in cities across Bangladesh can be broadly classified into non-auto (pedal-powered) and auto-rickshaws (motorized). Monitoring the movement of auto-rickshaws is necessary as traffic rules often restrict auto-rickshaws from accessing certain routes. However, existing surveillance systems make it quite difficult to monitor them due to their similarity to other vehicles, especially non-auto rickshaws whereas manual video analysis is too time-consuming. This paper presents a machine learning-based approach to automatically detect auto-rickshaws in traffic images. In this system, we used real-time object detection using the YOLOv8 model. For training purposes, we prepared a set of 1,730 annotated images that were captured under various traffic conditions. The results show that our proposed model performs well in real-time auto-rickshaw detection and offers an mAP50 of 83.447% and binary precision and recall values above 78%, demonstrating its effectiveness in handling both dense and sparse traffic scenarios. The dataset has been publicly released for further research.
Read the full abstract

All authors Sudipto Das Sukanto, Diponker Roy, Fahim Shakil, Nirjhar Singha, Abdullah Asik, Aniket Joarder, Mridha Md Nafis Fuad, Muhammad Ibrahim

Computer Vision

MV-MLM: Bridging Multi-View Mammography and Language for Breast Cancer Diagnosis and Risk Prediction

Large annotated datasets are essential for training robust Computer-Aided Diagnosis (CAD) models for breast cancer detection or risk prediction. However, acquiring such datasets with fine-detailed annotation is both costly and time-consuming. Vision-Language Models (VLMs), such as CLIP, which are pre-trained on large image-text pairs, offer a promising solution by enhancing robustness and data efficiency in medical imaging tasks. This paper introduces a novel Multi-View Mammography and Language Model for breast cancer classification and risk prediction, trained on a dataset of paired mammogram images and synthetic radiology reports. Our MV-MLM leverages multi-view supervision to learn rich representations from extensive radiology data by employing cross-modal self-supervision across image-text pairs. This includes multiple views and the corresponding pseudo-radiology reports. We propose a novel joint visual-textual learning strategy to enhance generalization and accuracy performance over different data types and tasks to distinguish breast tissues or cancer characteristics(calcification, mass) and utilize these patterns to understand mammography images and predict cancer risk. We evaluated our method on both private and publicly available datasets, demonstrating that the proposed model achieves state-of-the-art performance in three classification tasks: (1) malignancy classification, (2) subtype classification, and (3) image-based cancer risk prediction. Furthermore, the model exhibits strong data efficiency, outperforming existing fully supervised or VLM baselines while trained on synthetic text reports and without the need for actual radiology reports.
Read the full abstract

All authors Shunjie-Fabian Zheng, Hyeonjun Lee, Thijs Kooi, Ali Diba

Computer Vision

BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation

Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we propose a strong baseline BasicAVSR for AVSR by integrating four key components: 1) adaptive multi-scale frequency priors generated from image Laplacian pyramids, 2) a flow-guided propagation unit to aggregate spatiotemporal information from adjacent frames, 3) a second-order motion compensation unit for more accurate spatial alignment of adjacent frames, and 4) a hyper-upsampling unit to generate scale-aware and content-independent upsampling kernels. To meet diverse application demands, we instantiate three propagation variants: (i) a unidirectional RNN unit for strictly online inference, (ii) a unidirectional RNN unit empowered with a limited lookahead that tolerates a small output delay, and (iii) a bidirectional RNN unit designed for offline tasks where computational resources are less constrained. Experimental results demonstrate the effectiveness and adaptability of our model across these different scenarios. Through extensive experiments, we show that BasicAVSR significantly outperforms existing methods in terms of super-resolution quality, generalization ability, and inference speed. Our work not only advances the state-of-the-art in AVSR but also extends its core components to multiple frameworks for diverse scenarios. The code is available at https://github.com/shangwei5/BasicAVSR.
Read the full abstract

All authors Wei Shang, Wanying Zhang, Shuhang Gu, Pengfei Zhu, Qinghua Hu, Dongwei Ren

Computer Vision · Cross-listed from cs.GR

StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement

Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures. The code is publicly available at %\href{https://github.com/Teagrus/StructLayoutFormer} {https://github.com/Teagrus/StructLayoutFormer}.
Read the full abstract

All authors Xin Hu, Pengfei Xu, Jin Zhou, Hongbo Fu, Hui Huang

Computer Vision

FullPart: Generating each 3D Part at Full Resolution

Part-based 3D generation holds great potential for various applications. Previous part generators that represent parts using implicit vector-set tokens often suffer from insufficient geometric details. Another line of work adopts an explicit voxel representation but shares a global voxel grid among all parts; this often causes small parts to occupy too few voxels, leading to degraded quality. In this paper, we propose FullPart, a novel framework that combines both implicit and explicit paradigms. It first derives the bounding box layout through an implicit box vector-set diffusion process, a task that implicit diffusion handles effectively since box tokens contain little geometric detail. Then, it generates detailed parts, each within its own fixed full-resolution voxel grid. Instead of sharing a global low-resolution space, each part in our method - even small ones - is generated at full resolution, enabling the synthesis of intricate details. We further introduce a center-point encoding strategy to address the misalignment issue when exchanging information between parts of different actual sizes, thereby maintaining global coherence. Moreover, to tackle the scarcity of reliable part data, we present PartVerse-XL, the largest human-annotated 3D part dataset to date with 40K objects and 320K parts. Extensive experiments demonstrate that FullPart achieves state-of-the-art results in 3D part generation. We will release all code, data, and model to benefit future research in 3D part generation.
Read the full abstract

All authors Lihe Ding, Shaocong Dong, Yaokun Li, Chenjian Gao, Xiao Chen, Rui Han, Yihao Kuang, Hong Zhang, Bo Huang, Zhanpeng Huang, Zibin Wang, Dan Xu, Tianfan Xue

Computer Vision

Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM

Attention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, provide visual insights into the reasoning of convolutional neural networks (CNNs). Using network gradients, it is possible to identify regions where the network pays attention during image recognition tasks. Furthermore, these gradients can be combined with CNN features to localize more generalizable, task-specific attentive (salient) regions within scenes. However, explicit use of this gradient-based attention information integrated directly into CNN representations for semantic object understanding remains limited. Such integration is particularly beneficial for visual tasks like simultaneous localization and mapping (SLAM), where CNN representations enriched with spatially attentive object locations can enhance performance. In this work, we propose utilizing task-specific network attention for RGB-D indoor SLAM. Specifically, we integrate layer-wise attention information derived from network gradients with CNN feature representations to improve frame association performance. Experimental results indicate improved performance compared to baseline methods, particularly for large environments.
Read the full abstract

All authors Ali Caglayan, Nevrez Imamoglu, Oguzhan Guclu, Ali Osman Serhatoglu, Ahmet Burak Can, Ryosuke Nakamura

Computer Vision

WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios

Vision-based end-to-end (E2E) driving has garnered significant interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios, failing to adequately test the true potential of these systems. Furthermore, existing open-loop evaluation metrics often fall short in capturing the multi-modal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that that are rare in daily life with an occurring frequency of less than 0.03%. Concretely, each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate the E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional metrics that measure the distance between predicted way points and the logs, RFS measures how closely the predicted trajectory matches rater-annotated trajectory preference labels. We have released rater preference labels for all WOD-E2E validation set segments, while the held out test set labels have been used for the 2025 WOD-E2E Challenge. Through our work, we aim to foster state of the art research into generalizable, robust, and safe end-to-end autonomous driving agents capable of handling complex real-world situations.
Read the full abstract

All authors Runsheng Xu, Hubert Lin, Wonseok Jeon, Hao Feng, Yuliang Zou, Liting Sun, John Gorman, Ekaterina Tolstaya, Sarah Tang, Brandyn White, Ben Sapp, Mingxing Tan, Jyh-Jing Hwang, Dragomir Anguelov

Computer Vision

JOGS: Joint Optimization of Pose Estimation and 3D Gaussian Splatting

Traditional novel view synthesis methods heavily rely on external camera pose estimation tools such as COLMAP, which often introduce computational bottlenecks and propagate errors. To address these challenges, we propose a unified framework that jointly optimizes 3D Gaussian points and camera poses without requiring pre-calibrated inputs. Our approach iteratively refines 3D Gaussian parameters and updates camera poses through a novel co-optimization strategy, ensuring simultaneous improvements in scene reconstruction fidelity and pose estimation accuracy. The key innovation lies in decoupling the joint optimization into two interleaved phases: first, updating 3D Gaussian parameters via differentiable rendering with fixed poses, and second, refining camera poses using a customized 3D optical flow algorithm that incorporates geometric and photometric constraints. This formulation progressively reduces projection errors, particularly in challenging scenarios with large viewpoint variations and sparse feature distributions, where traditional methods struggle. Extensive evaluations on multiple datasets demonstrate that our approach significantly outperforms existing COLMAP-free techniques in reconstruction quality, and also surpasses the standard COLMAP-based baseline in general.
Read the full abstract

All authors Xianben Yang, Yuxuan Li, Tao Wang, Tao Wang, Yi Jin, Yidong Li, Haibin Ling

Computer Vision

OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research

As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottleneck, as scholars often spend substantial effort searching for, compiling, and managing relevant resources. To address these challenges, we present OracleAgent, the first agent system designed for the structured management and retrieval of OBS-related information. OracleAgent seamlessly integrates multiple OBS analysis tools, empowered by large language models (LLMs), and can flexibly orchestrate these components. Additionally, we construct a comprehensive domain-specific multimodal knowledge base for OBS, which is built through a rigorous multi-year process of data collection, cleaning, and expert annotation. The knowledge base comprises over 1.4M single-character rubbing images and 80K interpretation texts. OracleAgent leverages this resource through its multimodal tools to assist experts in retrieval tasks of character, document, interpretation text, and rubbing image. Extensive experiments demonstrate that OracleAgent achieves superior performance across a range of multimodal reasoning and generation tasks, surpassing leading mainstream multimodal large language models (MLLMs) (e.g., GPT-4o). Furthermore, our case study illustrates that OracleAgent can effectively assist domain experts, significantly reducing the time cost of OBS research. These results highlight OracleAgent as a significant step toward the practical deployment of OBS-assisted research and automated interpretation systems.
Read the full abstract

All authors Caoshuo Li, Zengmao Ding, Xiaobin Hu, Bang Li, Donghao Luo, Xu Peng, Taisong Jin, Yongge Liu, Shengwei Han, Jing Yang, Xiaoping He, Feng Gao, AndyPian Wu, SevenShu, Chaoyang Wang, Chengjie Wang

Computer Vision

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introduce EgoExo-Con(sistency), a benchmark of synchronized egocentric and exocentric video pairs with human-refined queries that ensure all concepts are visible in both viewpoints. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Grounding. It evaluates not only correctness but consistency across viewpoints. Our analysis reveals two critical limitations of existing Video-LLMs: (1) models often fail to maintain consistency, with results far worse than their single-view performances. (2) When naively finetuned with synchronized videos of both viewpoints, the models show improved consistency but often underperform those trained on a single view. For improvements, we propose View-GRPO, a novel reinforcement learning framework that effectively strengthens view-specific temporal reasoning while encouraging consistent comprehension across viewpoints. Our method demonstrates its superior temporal understanding capabilities, especially for improving cross-view consistency. All resources have been made available at https://minjoong507.github.io/projects/EgoExo-Con/
Read the full abstract

All authors Minjoon Jung, Junbin Xiao, Junghyun Kim, Byoung-Tak Zhang, Angela Yao

Computer Vision

Security Risk of Misalignment between Text and Image in Multi-modal Model

Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the alignment between textual and Image modalities in existing diffusion models is inadequate. This misalignment presents significant risks, especially in the generation of inappropriate or Not-Safe-For-Work (NSFW) content. To this end, we propose a novel attack called Prompt-Restricted Multi-modal Attack (PReMA) to manipulate the generated content by modifying the input image in conjunction with any specified prompt, without altering the prompt itself. PReMA is the first attack that manipulates model outputs by solely creating adversarial images, distinguishing itself from prior methods that primarily generate adversarial prompts to produce NSFW content. Consequently, PReMA poses a novel threat to the integrity of multi-modal diffusion models, particularly in image-editing applications that operate with fixed prompts. Comprehensive evaluations conducted on image inpainting and style transfer tasks across various models confirm the potent efficacy of PReMA.
Read the full abstract

Computer Vision

Dynamic VLM-Guided Negative Prompting for Diffusion Models

We propose a novel approach for dynamic negative prompting in diffusion models that leverages Vision-Language Models (VLMs) to adaptively generate negative prompts during the denoising process. Unlike traditional Negative Prompting methods that use fixed negative prompts, our method generates intermediate image predictions at specific denoising steps and queries a VLM to produce contextually appropriate negative prompts. We evaluate our approach on various benchmark datasets and demonstrate the trade-offs between negative guidance strength and text-image alignment.
Read the full abstract

Computer Vision

FlexICL: A Flexible Visual In-context Learning Framework for Elbow and Wrist Ultrasound Segmentation

Elbow and wrist fractures are the most common fractures in pediatric populations. Automatic segmentation of musculoskeletal structures in ultrasound (US) can improve diagnostic accuracy and treatment planning. Fractures appear as cortical defects but require expert interpretation. Deep learning (DL) can provide real-time feedback and highlight key structures, helping lightly trained users perform exams more confidently. However, pixel-wise expert annotations for training remain time-consuming and costly. To address this challenge, we propose FlexICL, a novel and flexible in-context learning (ICL) framework for segmenting bony regions in US images. We apply it to an intra-video segmentation setting, where experts annotate only a small subset of frames, and the model segments unseen frames. We systematically investigate various image concatenation techniques and training strategies for visual ICL and introduce novel concatenation methods that significantly enhance model performance with limited labeled data. By integrating multiple augmentation strategies, FlexICL achieves robust segmentation performance across four wrist and elbow US datasets while requiring only 5% of the training images. It outperforms state-of-the-art visual ICL models like Painter, MAE-VQGAN, and conventional segmentation models like U-Net and TransUNet by 1-27% Dice coefficient on 1,252 US sweeps. These initial results highlight the potential of FlexICL as an efficient and scalable solution for US image segmentation well suited for medical imaging use cases where labeled data is scarce.
Read the full abstract

All authors Yuyue Zhou, Jessica Knight, Shrimanti Ghosh, Banafshe Felfeliyan, Jacob L. Jaremko, Abhilash R. Hareendranathan

Computer Vision · Cross-listed from cs.LG

Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data remains underexplored. This study investigates the effect of knowledge distillation on the transferability of “debiasing” capabilities from teacher models to student models on natural language inference (NLI) and image classification tasks. Through extensive experiments, we illustrate several key findings: (i) overall the debiasing capability of a model is undermined post-KD; (ii) training a debiased model does not benefit from injecting teacher knowledge; (iii) although the overall robustness of a model may remain stable post-distillation, significant variations can occur across different types of biases; and (iv) we pin-point the internal attention pattern and circuit that causes the distinct behavior post-KD. Given the above findings, we propose three effective solutions to improve the distillability of debiasing methods: developing high quality data for augmentation, implementing iterative knowledge distillation, and initializing student models with weights obtained from teacher models. To the best of our knowledge, this is the first study on the effect of KD on debiasing and its interenal mechanism at scale. Our findings provide understandings on how KD works and how to design better debiasing methods.
Read the full abstract

Wednesday 29 October

Computer Vision · Cross-listed from q-bio.QM

Selective Diabetic Retinopathy Screening with Accuracy-Weighted Deep Ensembles and Entropy-Guided Abstention

Diabetic retinopathy (DR), a microvascular complication of diabetes and a leading cause of preventable blindness, is projected to affect more than 130 million individuals worldwide by 2030. Early identification is essential to reduce irreversible vision loss, yet current diagnostic workflows rely on methods such as fundus photography and expert review, which remain costly and resource-intensive. This, combined with DR's asymptomatic nature, results in its underdiagnosis rate of approximately 25 percent. Although convolutional neural networks (CNNs) have demonstrated strong performance in medical imaging tasks, limited interpretability and the absence of uncertainty quantification restrict clinical reliability. Therefore, in this study, a deep ensemble learning framework integrated with uncertainty estimation is introduced to improve robustness, transparency, and scalability in DR detection. The ensemble incorporates seven CNN architectures-ResNet-50, DenseNet-121, MobileNetV3 (Small and Large), and EfficientNet (B0, B2, B3)- whose outputs are fused through an accuracy-weighted majority voting strategy. A probability-weighted entropy metric quantifies prediction uncertainty, enabling low-confidence samples to be excluded or flagged for additional review. Training and validation on 35,000 EyePACS retinal fundus images produced an unfiltered accuracy of 93.70 percent (F1 = 0.9376). Uncertainty-filtering later was conducted to remove unconfident samples, resulting in maximum-accuracy of 99.44 percent (F1 = 0.9932). The framework shows that uncertainty-aware, accuracy-weighted ensembling improves reliability without hindering performance. With confidence-calibrated outputs and a tunable accuracy-coverage trade-off, it offers a generalizable paradigm for deploying trustworthy AI diagnostics in high-risk care.
Read the full abstract

Computer Vision

Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures

Rapid climate change and other disturbances in alpine ecosystems demand frequent habitat monitoring, yet manual mapping remains prohibitively expensive for the required temporal resolution. We employ deep learning for change detection using long-term alpine habitat data from Gesaeuse National Park, Austria, addressing a major gap in applying geospatial foundation models (GFMs) to complex natural environments with fuzzy class boundaries and highly imbalanced classes. We compare two paradigms: post-classification change detection (CD) versus direct CD. For post-classification CD, we evaluate GFMs Prithvi-EO-2.0 and Clay v1.0 against U-Net CNNs; for direct CD, we test the transformer ChangeViT against U-Net baselines. Using high-resolution multimodal data (RGB, NIR, LiDAR, terrain attributes) covering 4,480 documented changes over 15.3 km2, results show Clay v1.0 achieves 51% overall accuracy versus U-Net's 41% for multi-class habitat change, while both reach 67% for binary change detection. Direct CD yields superior IoU (0.53 vs 0.35) for binary but only 28% accuracy for multi-class detection. Cross-temporal evaluation reveals GFM robustness, with Clay maintaining 33% accuracy on 2020 data versus U-Net's 23%. Integrating LiDAR improves semantic segmentation from 30% to 50% accuracy. Although overall accuracies are lower than in more homogeneous landscapes, they reflect realistic performance for complex alpine habitats. Future work will integrate object-based post-processing and physical constraints to enhance applicability.
Read the full abstract

Computer Vision · Cross-listed from cs.IR

LookSync: Large-Scale Visual Product Search System for AI-Generated Fashion Looks

Generative AI is reshaping fashion by enabling virtual looks and avatars making it essential to find real products that best match AI-generated styles. We propose an end-to-end product search system that has been deployed in a real-world, internet scale which ensures that AI-generated looks presented to users are matched with the most visually and semantically similar products from the indexed vector space. The search pipeline is composed of four key components: query generation, vectorization, candidate retrieval, and reranking based on AI-generated looks. Recommendation quality is evaluated using human-judged accuracy scores. The system currently serves more than 350,000 AI Looks in production per day, covering diverse product categories across global markets of over 12 million products. In our experiments, we observed that across multiple annotators and categories, CLIP outperformed alternative models by a small relative margin of 3–7% in mean opinion scores. These improvements, though modest in absolute numbers, resulted in noticeably better user perception matches, establishing CLIP as the most reliable backbone for production deployment.
Read the full abstract

All authors Pradeep M, Ritesh Pallod, Satyen Abrol, Muthu Raman, Ian Anderson

Computer Vision · Cross-listed from cs.SD

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.
Read the full abstract

All authors Jiarong Du, Zhan Jin, Peijun Yang, Juan Liu, Zhuo Li, Xin Liu, Ming Li

Computer Vision

Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures have critical limitations in temporal understanding, struggling with tasks that require detailed comprehension of action sequences and temporal progression. In this work, we propose a Video-LLM architecture that introduces stacked temporal attention modules directly within the vision encoder. This design incorporates a temporal attention in vision encoder, enabling the model to better capture the progression of actions and the relationships between frames before passing visual tokens to the LLM. Our results show that this approach significantly improves temporal reasoning and outperforms existing models in video question answering tasks, specifically in action recognition. We improve on benchmarks including VITATECS, MVBench, and Video-MME by up to +5.5%. By enhancing the vision encoder with temporal structure, we address a critical gap in video understanding for Video-LLMs. Project page and code are available at: https://alirasekh.github.io/STAVEQ2/.
Read the full abstract

All authors Ali Rasekh, Erfan Bagheri Soula, Omid Daliran, Simon Gottschalk, Mohsen Fayyaz

Computer Vision · Cross-listed from eess.IV

Groupwise Registration with Physics-Informed Test-Time Adaptation on Multi-parametric Cardiac MRI

Multiparametric mapping MRI has become a viable tool for myocardial tissue characterization. However, misalignment between multiparametric maps makes pixel-wise analysis challenging. To address this challenge, we developed a generalizable physics-informed deep-learning model using test-time adaptation to enable group image registration across contrast weighted images acquired from multiple physical models (e.g., a T1 mapping model and T2 mapping model). The physics-informed adaptation utilized the synthetic images from specific physics model as registration reference, allows for transductive learning for various tissue contrast. We validated the model in healthy volunteers with various MRI sequences, demonstrating its improvement for multi-modal registration with a wide range of image contrast variability.
Read the full abstract

All authors Xinqi Li, Yi Zhang, Li-Ting Huang, Hsiao-Huang Chang, Thoralf Niendorf, Min-Chi Ku, Qian Tao, Hsin-Jung Yang

Computer Vision

Climate Adaptation-Aware Flood Prediction for Coastal Cities Using Deep Learning

Climate change and sea-level rise (SLR) pose escalating threats to coastal cities, intensifying the need for efficient and accurate methods to predict potential flood hazards. Traditional physics-based hydrodynamic simulators, although precise, are computationally expensive and impractical for city-scale coastal planning applications. Deep Learning (DL) techniques offer promising alternatives, however, they are often constrained by challenges such as data scarcity and high-dimensional output requirements. Leveraging a recently proposed vision-based, low-resource DL framework, we develop a novel, lightweight Convolutional Neural Network (CNN)-based model designed to predict coastal flooding under variable SLR projections and shoreline adaptation scenarios. Furthermore, we demonstrate the ability of the model to generalize across diverse geographical contexts by utilizing datasets from two distinct regions: Abu Dhabi and San Francisco. Our findings demonstrate that the proposed model significantly outperforms state-of-the-art methods, reducing the mean absolute error (MAE) in predicted flood depth maps on average by nearly 20%. These results highlight the potential of our approach to serve as a scalable and practical tool for coastal flood management, empowering decision-makers to develop effective mitigation strategies in response to the growing impacts of climate change. Project Page: https://caspiannet.github.io/
Read the full abstract

All authors Bilal Hassan, Areg Karapetyan, Aaron Chung Hin Chow, Samer Madanat

Computer Vision

CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments

Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or unrealistic, synthetically generated anomalies, failing to capture the richness and unpredictability of real-world anomalies. In this work, we introduce CAVE, the first benchmark of real-world visual anomalies. CAVE supports three open-ended tasks: anomaly description, explanation, and justification; with fine-grained annotations for visual grounding and categorizing anomalies based on their visual manifestations, their complexity, severity, and commonness. These annotations draw inspiration from cognitive science research on how humans identify and resolve anomalies, providing a comprehensive framework for evaluating Vision-Language Models (VLMs) in detecting and understanding anomalies. We show that state-of-the-art VLMs struggle with visual anomaly perception and commonsense reasoning, even with advanced prompting strategies. By offering a realistic and cognitively grounded benchmark, CAVE serves as a valuable resource for advancing research in anomaly detection and commonsense reasoning in VLMs.
Read the full abstract

All authors Rishika Bhagwatkar, Syrielle Montariol, Angelika Romanou, Beatriz Borges, Irina Rish, Antoine Bosselut

Computer Vision · Cross-listed from cs.RO

DARTS: A Drone-Based AI-Powered Real-Time Traffic Incident Detection System

Rapid and reliable incident detection is critical for reducing crash-related fatalities, injuries, and congestion. However, conventional methods, such as closed-circuit television, dashcam footage, and sensor-based detection, separate detection from verification, suffer from limited flexibility, and require dense infrastructure or high penetration rates, restricting adaptability and scalability to shifting incident hotspots. To overcome these challenges, we developed DARTS, a drone-based, AI-powered real-time traffic incident detection system. DARTS integrates drones' high mobility and aerial perspective for adaptive surveillance, thermal imaging for better low-visibility performance and privacy protection, and a lightweight deep learning framework for real-time vehicle trajectory extraction and incident detection. The system achieved 99% detection accuracy on a self-collected dataset and supports simultaneous online visual verification, severity assessment, and incident-induced congestion propagation monitoring via a web-based interface. In a field test on Interstate 75 in Florida, DARTS detected and verified a rear-end collision 12 minutes earlier than the local transportation management center and monitored incident-induced congestion propagation, suggesting potential to support faster emergency response and enable proactive traffic control to reduce congestion and secondary crash risk. Crucially, DARTS's flexible deployment architecture reduces dependence on frequent physical patrols, indicating potential scalability and cost-effectiveness for use in remote areas and resource-constrained settings. This study presents a promising step toward a more flexible and integrated real-time traffic incident detection system, with significant implications for the operational efficiency and responsiveness of modern transportation management.
Read the full abstract

All authors Bai Li, Achilleas Kourtellis, Rong Cao, Joseph Post, Brian Porter, Yu Zhang

Computer Vision

Larger Hausdorff Dimension in Scanning Pattern Facilitates Mamba-Based Methods in Low-Light Image Enhancement

We propose an innovative enhancement to the Mamba framework by increasing the Hausdorff dimension of its scanning pattern through a novel Hilbert Selective Scan mechanism. This mechanism explores the feature space more effectively, capturing intricate fine-scale details and improving overall coverage. As a result, it mitigates information inconsistencies while refining spatial locality to better capture subtle local interactions without sacrificing the model's ability to handle long-range dependencies. Extensive experiments on publicly available benchmarks demonstrate that our approach significantly improves both the quantitative metrics and qualitative visual fidelity of existing Mamba-based low-light image enhancement methods, all while reducing computational resource consumption and shortening inference time. We believe that this refined strategy not only advances the state-of-the-art in low-light image enhancement but also holds promise for broader applications in fields that leverage Mamba-based techniques.
Read the full abstract

All authors Xinhua Wang, Caibo Feng, Xiangjun Fu, Chunxiao Liu

Computer Vision

Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI

In this work, we address the TrackRAD2025 challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints. Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1 and its recent variants through prompt-based interaction. Due to the one-second runtime constraint, the SAM-based method was ultimately selected. The final configuration used SAM2.1 b+ with mask-based prompts from the first annotated slice, fine-tuned solely on the small labeled subset from TrackRAD2025. Training was configured to minimize overfitting, using 1024x1024 patches (batch size 1), standard augmentations, and a balanced Dice + IoU loss. A low uniform learning rate (0.0001) was applied to all modules (prompt encoder, decoder, Hiera backbone) to preserve generalization while adapting to annotator-specific styles. Training lasted 300 epochs (~12h on RTX A6000, 48GB). The same inference strategy was consistently applied across all anatomical sites and MRI field strengths. Test-time augmentation was considered but ultimately discarded due to negligible performance gains. The final model was selected based on the highest Dice Similarity Coefficient achieved on the validation set after fine-tuning. On the hidden test set, the model reached a Dice score of 0.8794, ranking 6th overall in the TrackRAD2025 challenge. These results highlight the strong potential of foundation models for accurate and real-time tumor tracking in MRI-guided radiotherapy.
Read the full abstract

All authors Valentin Boussot, Cédric Hémon, Jean-Claude Nunes, Jean-Louis Dillenseger

Computer Vision

Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer

Reconstructing images seen by people from their fMRI brain recordings provides a non-invasive window into the human brain. Despite recent progress enabled by diffusion models, current methods often lack faithfulness to the actual seen images. We present "Brain-IT", a brain-inspired approach that addresses this challenge through a Brain Interaction Transformer (BIT), allowing effective interactions between clusters of functionally-similar brain-voxels. These functional-clusters are shared by all subjects, serving as building blocks for integrating information both within and across brains. All model components are shared by all clusters & subjects, allowing efficient training with a limited amount of data. To guide the image reconstruction, BIT predicts two complementary localized patch-level image features: (i)high-level semantic features which steer the diffusion model toward the correct semantic content of the image; and (ii)low-level structural features which help to initialize the diffusion process with the correct coarse layout of the image. BIT's design enables direct flow of information from brain-voxel clusters to localized image features. Through these principles, our method achieves image reconstructions from fMRI that faithfully reconstruct the seen images, and surpass current SotA approaches both visually and by standard objective metrics. Moreover, with only 1-hour of fMRI data from a new subject, we achieve results comparable to current methods trained on full 40-hour recordings.
Read the full abstract

All authors Roman Beliy, Amit Zalcher, Jonathan Kogman, Navve Wasserman, Michal Irani

Computer Vision

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing

Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing tasks: inaccurate inversion processes for mapping real images back into the latent space, and gradient entanglement issues during editing often result in outputs that do not faithfully reflect the target prompt. Recent efforts have attempted to directly map source and target distributions via ODE-based approaches without inversion; however,these methods still yield suboptimal editing quality. In this work, we propose a flow decomposition-and-aggregation framework built upon an inversion-free formulation to address these limitations. Specifically, we semantically decompose the target prompt into multiple sub-prompts, compute an independent flow for each, and aggregate them to form a unified editing trajectory. While we empirically observe that decomposing the original flow enhances diversity in the target space, generating semantically aligned outputs still requires consistent guidance toward the full target prompt. To this end, we design a projection and soft-aggregation mechanism for flow, inspired by gradient conflict resolution in multi-task learning. This approach adaptively weights the sub-target velocity fields, suppressing semantic redundancy while emphasizing distinct directions, thereby preserving both diversity and consistency in the final edited output. Experimental results demonstrate that our method outperforms existing zero-shot editing approaches in terms of semantic fidelity and attribute disentanglement. The code is available at https://github.com/Harvard-AI-and-Robotics-Lab/SplitFlow.
Read the full abstract

All authors Sung-Hoon Yoon, Minghan Li, Gaspard Beaudouin, Congcong Wen, Muhammad Rafay Azhar, Mengyu Wang