cs.CV · 2026-06-29 · No. 38
Computer Vision and Pattern Recognition, 2026-06-29.
30 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
30 entries-
01
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
Ali Zia, Usman Ali, Abdul Rehman, Umer Ramzan, Kang Han, Muhammad Faheem, Shahnawaz Qureshi, Wei Xiang
cs.CV · cs.AI
Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models. However, existing TTA approaches for anomaly segmentation remain limited by their reliance on pixel-level heuristics, such as confidence thresholding or entropy minimisation, which fail to preserve structural consistency under noise and texture variation. Moreover, they typically treat anomaly maps as flat intensity fields,...
-
02
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei...
cs.CV · cs.AI
Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference. Existing mitigation strategies typically rely on static constraints or external heuristics. In this work, we propose that exposure bias itself inherently contains dynamic signals that can guide its own rectification. To leverage this, we introduce DEFAR (DirEctional-Frequency Adaptive...
-
03
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
Jiaxin Li, Yuxiang Wu, Zhenkai Zhang, Xinrui Shi, Haoyuan Wang, Yichen Zhao, Su Linxiang, Chenyang Yu, Mingyu Zhang,...
cs.CV · cs.AI · cs.GR
Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe occlusions and complex dynamics inherent in multi-object interactions. To bridge this gap, we propose HAT-4D, the first agentic framework designed...
-
04
EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography
Darya Taratynova, Ahmed Aly, Numan Saeed, Mohammad Yaqub
cs.CV · cs.LG
Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis. Interpreting an echocardiogram requires synthesizing complementary evidence across multiple heart views to identify abnormalities and produce structured clinical reports. While recent efforts focus on improving classification performance, most models lack explicit diagnostic reasoning and spatially...
-
05
Toward Robust In-Context Segmentation via Concept Guidance
Zhigang Chen, Xiawu Zheng, Rongrong Ji
cs.CV · cs.AI
In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding masks, without updating any parameters. Despite recent progress, prior ICS studies have largely overlooked a critical aspect: system robustness, ie, whether the model can produce stable segmentation results for the same query under different references. In this work, we revisit ICS from the...
-
06
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Peiwen Zhang, Yufan Deng, Shangkun Sun, Juncheng Ma, Duomin Wang, Jonas Du, Zilin Pan, Ye Huang, Hao Liang, Songyan...
cs.CV · cs.AI · cs.RO
Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models can still produce physically implausible manipulations, including discontinuous motion trajectories and inconsistent robot-object interactions, which limits their reliability as world simulators. Through extensive experiments, we find that such physical instability...
-
07
BiDeMem: Bidirectional Degradation Memory for Explainable Image Restoration
Xinrui Wu, Lichen Huang
cs.CV · cs.AI
Degradation-aware prompts, conditions, and latent priors are increasingly used in image restoration, yet they are usually judged by a single endpoint: whether the restored image obtains higher PSNR. This is a weak test of semantics. A condition can help by adding capacity, acting as a global correction bias, or exploiting dataset shortcuts, without becoming an interpretable degradation prior. We propose BiDeMem, a bidirectional degradation...
-
08
Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Training
Francis Xiatian Zhang, Hao Yao, Shengxuan Chen, Hong Zhu, Hongxiao Jia, Sisi Zheng, Hubert P. H. Shum
cs.CV · cs.LG
Vision-based assessment can provide convenient and cost-effective evaluation in Traditional Chinese Medicine (TCM) rehabilitation training, where action quality assessment (AQA) from computer vision offers a promising solution. Existing automatic AQA frameworks for physical therapy typically rely on skeletal data captured from a single viewpoint, which is inefficient for TCM techniques such as acupuncture or Tuina that involve dense hand...
-
09
OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal
Qinming Zhou, Chenxi Sun, Deyang Kong, Junhao He, Xiangheng Tang, Peike Yu, Haotian Wu, Leilei Cao, Linfeng Zhang
cs.CV · cs.AI
Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the fact that user-provided masks are often inaccurate or incomplete. With billions of parameters and tens of denoising steps, diffusion-based models achieve strong removal performance at the expense of substantial computational cost, limiting their use in interactive...
-
10
STAG: Spatio-temporal Evolving Structural Representation of Action Units for Micro-expression Recognition
Nandani Sharma, Varun Sharma, Dinesh Singh
cs.CV · cs.AI · cs.GR · cs.HC · cs.MM
Micro-expression recognition is challenging due to subtle and short-lived facial muscle movements. Existing methods rely heavily on apex-onset frames, overlook fine-grained inter-frame dynamics, and separately model spatial and temporal information, limiting generalization across datasets. To address these challenges, we propose STAG, a dynamic ROI-AU-coupled spatial-temporal network that jointly models motion flow and adaptive facial...
-
11
Mind the Gap: Quantifying the Domain Gap in Cross-Sensor Diffusion Super-Resolution
Dawid Kopeć, Katarzyna Jabłońska, Wojciech Kozłowski, Maciej Zięba
cs.CV · cs.AI
Demand for high-resolution satellite imagery has increased interest in super-resolution (SR) to bridge the spatial resolution gap between freely available missions such as Sentinel-2 and commercial systems like PlanetScope. Because no sensor provides true paired low- and high-resolution observations, SR models are usually trained on synthetically degraded data, creating a domain gap on real cross-sensor imagery. In this work, we provide the...
-
12
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
Jiayi Xu, Di He, Guolin Ke
cs.CV · cs.AI
Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches, avoiding discrete tokenization or a separately pretrained tokenizer. However, it faces coupled challenges: high-dimensional patch generation causes large single-step errors, and teacher-forced training creates a train--inference gap that makes these errors accumulate across AR steps. Existing fixes such as $x$-prediction and...
-
13
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
ZhengXian Wu, Hangrui Xu, Kai Shi, Zhuohong Chen, Yunyao Yu, Chuanrui Zhang, Zirui Liao, Jun Yang, Zhenyu Yang,...
cs.CV · cs.AI
Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pipeline with a pre-selected retriever and a static top-k setting, which is not adaptive during reasoning. We propose ProMSA, a progressive multimodal search agent for KB-VQA. Given an image-question pair, the agent iteratively chooses image search, text search, or...
-
14
Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
Yiyun Fei, Guoqiu Li, Jin Song, Chuqiao Wu, Delong Wu, Hong Wu, Ziru Zeng, Haohui Chen, YinDong Kong, Jing Li, Qi...
cs.CV · cs.AI
We present Home3D 1.0, a modular image-to-3D generation system that produces high-quality 3D assets from a single reference image, targeting interior design and e-commerce applications. Given a photograph of a furniture or decor item, the system outputs a mesh with physically-based rendering (PBR) materials, and the mesh can be decomposed into material-specific components. The pipeline is organized into four tightly coupled modules: Geometry...
-
15
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
Shuimu Chen, Yuteng Chen, Yuanshen Guan, Zebang Cheng, Zeyu Zhang, Shengqian Qin, Bin Xia, Jiaran Li, Wenming Yang, Fei Ma
cs.CV · cs.AI
Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters. Lacking objective external evidence, models are frequently trapped in blind confidence and often fail to correct errors. Furthermore, applying reinforcement learning to multi-stage reflection pipelines introduces severe policy coupling, which is exacerbated by a critical scarcity of dedicated...
-
16
Every Step of the Way: Video-based Parkinsonian Turning Step Counting
Qiushuo Cheng, Jingjing Liu, Catherine Morgan, Alan Whone, Majid Mirmehdi
cs.CV · cs.AI
As a prominent symptom of Parkinson's disease (PD), turning impairment is evaluated through parameters such as turning angle, duration, and particularly, the number of steps required to complete a turn, which directly reflects motor dysfunction. Accurate step counting is challenging due to variability in real-world turning movements and atypical shuffling patterns in parkinsonian gait. Existing methods are predominantly wearable-based,...
-
17
SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion
Haoyu Zhang, Meng Liu, Qianlong Xiang, Kun Wang, Yaowei Wang, Liqiang Nie
cs.CV · cs.AI
Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation. However, existing UAV benchmarks often emphasize image-level recognition, single-view understanding, or narrow answer formats, leaving 3D spatial inference, multi-view collaboration, scene dynamics, and diverse task formulations insufficiently evaluated. To address these gaps, we introduce SpatialUAV, a real low-altitude...
-
18
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
Tīkun Ông, Georg Bökman
cs.CV · cs.LG
Vision transformers have become a dominant architecture for visual recognition. However, standard models do not explicitly encode the planar symmetries that arise in many vision domains. We introduce a family of vision transformers equivariant to arbitrary discrete subgroups of $\mathrm{O}(2)$, providing a unified framework that generalizes prior flipping- and $D_4$-equivariant transformer architectures. Our construction yields equivariant...
-
19
Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling
Zhaoning Shi, Bo Ma, Hao Xu, Zepeng Yang, Bo Liang
cs.CV · cs.AI
This paper addresses the lack of explicit memory mechanisms in current object detection models and proposes Hippocampus-DETR, a novel detection framework based on biological hippocampal memory modeling. This framework integrates a hippocampal memory network module, HipNet, into the DETR architecture and systematically simulates the anatomical structure and functional organization of hippocampal subregions, including the entorhinal cortex,...
-
20
Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy
Rixon Crane, Fahira Afzal Maken, Nicholas Lawrance, Stanislav Funiak, Kasra Khosoussi, Ming Xu, Russell Tsuchida
cs.CV · cs.LG
We present MMD-Reg, a novel correspondence-free approach to point-cloud registration that is differentiable and has linear computational complexity in the number of points. We model registration as a nonlinear least-squares problem based on the Maximum Mean Discrepancy, approximated using random Fourier features. The resulting objective can be solved efficiently with standard methods such as Levenberg-Marquardt, and the solution is...
-
21
Improving Adversarial Robustness via Activation Amplification and Attenuation
Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki, Shinichiro Omachi
cs.CV · cs.AI · cs.LG
The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, or feature recalibration, we instead propose to jointly learn to amplify and attenuate these signals through a simple activation scaling mechanism. To this end, we introduce Activation Amplification and Attenuation (A3), a lightweight plug-in module that enhances...
-
22
Joint Transcription and Decryption of Images of Encrypted Handwritten Documents: A Comparison with the Traditional Pipeline
Marino Oliveros-Blanco, Lei Kang, Alicia Fornés, Beáta Megyesi
cs.CV · cs.CL · cs.LG
Historical encrypted manuscripts present a challenging problem at the intersection of cryptology, linguistics, paleography, and computer vision. Current automatic decipherment approaches usually rely on a two-stage pipeline: transcription of cipher symbols from manuscript images, followed by decryption into plaintext. However, this design is sensitive to transcription errors, which propagate to the final output. We present Direct Image...
-
23
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
Brinnae Bent, Holly R. Houliston, Jiayi Zhou, Günel Aghakishiyeva, David W. Johnston
cs.CV · cs.AI · q-bio.QM
Artificial intelligence is transforming biodiversity monitoring by enabling automated analysis of ecological imagery collected from camera traps, drones, satellites, underwater platforms, and other sensing systems. These tools can expand the scale and speed of conservation assessments, yet many computer vision models remain difficult to inspect, making it challenging to determine whether predictions are based on ecologically meaningful...
-
24
Qwen-Image-2.0-RL Technical Report
Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan...
cs.CV · cs.LG
We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF) and on-policy distillation (OPD) to improve both the visual quality and instruction-following capability of the Qwen-Image-2.0 diffusion model. To provide reliable reward signals, we construct task-specific composite reward models by fine-tuning vision-language models with a pointwise scoring paradigm and chain-of-thought...
-
25
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Liu Yu, Can Chen, Ping Kuang, Zhikun Feng, Fan Zhou, Gillian Dobbie
cs.CV · cs.AI
Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination. Deviating from the prevailing attention intensity assumption, we reveal a deeper dynamic structural misalignment: hallucination is triggered at decision-critical steps where specific attention heads, acting as risky mediators, decouple from visual evidence to lock onto language priors. This establishes a pathological shortcut...
-
26
CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
Hana Kim, Minje Kim, Tae-Kyun Kim
cs.CV · cs.AI
3D scene inpainting is essential for reconstructing areas corrupted by occlusions or limited viewpoints. While recent methods leverage Gaussian Splatting (GS) for efficient 3D editing, they often depend on precise multi-view segmentation masks and are inherently constrained to object removal tasks. We propose CoIn, a novel framework that bridges 2D inpainting models and 3DGS through a multi-stage consistency pipeline. Our approach first...
-
27
Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC
Krzysztof Pysz, Artur Bartczak, Jarosław Kwiecień, Piotr Krajewski, Witold Dyrka
cs.CV · cs.AI · cs.LG · q-bio.TO
Accurate assessment of tumor proportion score (TPS) in non-small cell lung cancer (NSCLC) is critical for treatment planning and prognosis. Key challenges include the tedious manual work required to annotate each slide, combined with the limited number of experts certified for this task. Multiple instance learning (MIL) has proven to be an effective approach for predicting TPS scores at the slide level; however, existing methods struggle with...
-
28
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
Thomas Shih-Chao Liang, Zhuoran Yu, Yong Jae Lee
cs.CV · cs.AI · cs.LG
Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose LaViD--Language-to-Visual Knowledge Distillation--a simple and effective framework for transferring high-level semantic knowledge from a language-only teacher to a vision-only student model. Instead of relying on paired...
-
29
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Yujin Tang, Chenming Shang, Ruize Xu, Nikhil Singh
cs.CV · cs.AI · cs.CL
Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when an agent genuinely needs to remember what it saw rather than what it could write down. We introduce DMV-Bench (Code: https://github.com/yyyujintang/DMV-Bench), the first interactive benchmark for multimodal-agent visual memory. DMV-Bench is built on a controlled home-furnishing e-commerce...
-
30
DanceOPD: On-Policy Generative Field Distillation
Wei Zhou, Xiongwei Zhu, Zelin Xu, Bo Dong, Lixue Gong, Yongyuan Liang, Meng Chu, Leigang Qu, Lingdong Kong, Wei Liu,...
cs.CV · cs.CL · cs.LG
Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.