cs.CV · 2026-08-27 · No. 97

Computer Vision and Pattern Recognition, 2026-08-27.

27 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

27 entries
  1. 01

    VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

    Junxiang Xu, Ruisi Wang, Fanyi Pu, Maijunxian Wang, Ran Ji, Tongxi Zhou, Chenyang Gu, Jing Zuo, Hongcan Xiao, Yimeng...

    cs.CV · cs.AI · cs.LG · cs.MM · cs.RO

    Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-class substrates for problem solving beyond language. Yet progress remains bottlenecked by the lack of scalable training tasks, reliable feedback, and controlled comparisons across generative substrates. In this work, we introduce VBVR-Pro, a...

    arxiv.org/abs/2608.26105 · PDF

  2. 02

    A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training

    Kaichen Li, Zhilin Zhu, Jianhao Huang, Zhengqin Lai, Baochen Xiong, Zibo Shao, Yaguang Song, Linhui Xiao, Xiaoshan...

    cs.CV · cs.AI

    In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Existing unsupervised post-training methods for MLLMs typically optimize target tokens uniformly, overlooking their heterogeneous visual dependence (VD). However, we reveal that token-level VD is crucial for MU-CPT. Specifically, its structural distortion serves as an...

    arxiv.org/abs/2608.26095 · PDF

  3. 03

    MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching

    Hao Yin, Paritosh Parmar, Lijun Gu, Lin Xu, Tianxiao Guo, Xiujin Liu, Tianyou Zheng, Yang Zhang, Weiwei Fu

    cs.CV · cs.AI · cs.ET · cs.HC · cs.LG

    Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic patterns. These limitations hinder fine-grained, biomechanically grounded feedback. We introduce MyoMechanix, a multimodal ecosystem for weight-loaded actions that aligns motion with muscle activity. Expert-annotated, it contains...

    arxiv.org/abs/2608.26094 · PDF

  4. 04

    FRAME: separating sampling variation from representational cause in medical imaging fairness

    Mahshad Lotfinia, Daniel Truhn, Andreas Maier, Soroosh Tayebi Arasteh

    cs.CV · cs.AI · cs.LG

    Subgroup performance differences are the standard evidence for fairness bias in medical imaging, and the usual response removes the demographic information that a model encodes. Here we introduce Fair-model Reference And Mechanism Evaluation (FRAME), a two-step framework for auditing such a claim. The first step derives a fair-model reference, the distribution of the difference under exact fairness at the observed subgroup sizes. In the...

    arxiv.org/abs/2608.25981 · PDF

  5. 05

    PANDA - Prototype-Anchored Alignment for Partially Unpaired Multimodal Learning, with Applications to Alzheimers MRI and TCGA Pathology

    Sheethal Bhat, Mahfuzur Rahman Chowdhury, Paula Andrea Perez-Toro, Stephan Wunderlich, Rose Dawn Bharat, Siming...

    cs.CV · cs.AI

    Multimodal medical prediction often faces incomplete pairing: auxiliary modalities with complementary signal are available for only a subset of subjects (or none) and cannot be assumed at deployment. We introduce PANDA (Prototype Anchored Data Alignment), a two-stage framework that transfers auxiliary information to a primary-modality model without auxiliary inputs at inference. Stage 1 learns a shared embedding from the paired subset and...

    arxiv.org/abs/2608.25970 · PDF

  6. 06

    TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

    Yuqiang Lin, Yan Shi, Sam Lockyer, Harish Tayyar Madabushi, Adrian Evans, Wenbin Li, Yinhai Wang, Nic Zhang

    cs.CV · cs.AI

    Traffic Anomaly Understanding (TAU) requires models and systems to detect, reason about, and explain anomalous events in transportation videos. To address this challenge, we propose TAU-Agent, an agentic retrieval-augmented framework for traffic anomaly understanding. Given a task query, a central retrieval agent orchestrates two visual perception tools, namely a Video Captioning Tool and an Open-Vocabulary Tracking Tool, to retrieve and...

    arxiv.org/abs/2608.25935 · PDF

  7. 07

    When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated Images

    Ruoqi Hu, Chulin Zhao, Jiashuo Chang, Ramon Ruiz-Dolz, Hanhe Lin

    cs.CV · cs.AI

    *Chulin Zhao and Ruoqi Hu contributed equally to this work. State-of-the-art text-to-image (T2I) models exhibit pronounced and systematic defects when prompts involve intricate compositional factors such as multiple entities and multiple attributes. In this paper, we investigate how humans identify such defects. Specifically, we manually select 651 reference images from the four categories of people, hand, object, and scene that exhibit...

    arxiv.org/abs/2608.25933 · PDF

  8. 08

    Code World Model: Coding Agent as World Brain

    Yiwen Chen, Guosheng Lin, Chi Zhang

    cs.CV · cs.AI · cs.CL

    World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics from visual observations, which reveal outcomes rather than the underlying knowledge, rules, and mechanisms governing world evolution. This makes it difficult to maintain persistent consequences and support coherent, open-ended evolution. We introduce Code World Model, a framework that separates...

    arxiv.org/abs/2608.25927 · PDF

  9. 09

    Precipitation Downscaling Using Foundation Model-Conditioned Diffusion

    Victor Nascimento Ribeiro, Jorge Guevara, Jorge Sebastian Moraga, Chris Lucas, Natalie Lord, Andrew Taylor, Edward...

    cs.CV · cs.LG · physics.ao-ph

    High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for direct use. AI-based statistical downscaling with diffusion models offers a promising approach, but the mechanism by which large-scale atmospheric predictors condition generation remains largely unexplored. We investigate three conditioning strategies for a denoising diffusion probabilistic...

    arxiv.org/abs/2608.25858 · PDF

  10. 10

    FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstruction

    Tristan Gottwald, Michelle Bruch, Mubashir-Ul Hassan, Fatma Alickovic, Milan Kloiber, Daniel Tenbrinck, Torsten...

    cs.CV · cs.LG

    We present FlowMoDL, an unrolled neural network for highly accelerated 4D flow MRI reconstruction that directly optimizes for both anatomical magnitude and phase-derived velocity accuracy. Building on the MoDL framework, FlowMoDL alternates a learned (3+1)D spatiotemporal denoiser with conjugate-gradient data-consistency updates based on the SENSE forward model. A novel dual-pathway conditioning scheme adapts the denoiser features and...

    arxiv.org/abs/2608.25828 · PDF

  11. 11

    Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation

    Olasimbo Ayodeji Arigbabu, Abimbola Ismail Arigbabu

    cs.CV · cs.AI

    Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in...

    arxiv.org/abs/2608.25710 · PDF

  12. 12

    Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models

    Akshat G, Divyansh Gupta, Shaleen Bhatnagar, Shilpa Ankalaki, Tusar Kanti Mishra

    cs.CV · cs.AI · cs.LG

    Acquiring pixel-level annotations for medical image segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global anatomical structures, leading to boundary delineation failures in low-data regimes. This research paper proposes utilizing unsupervised Denoising Diffusion Probabilistic Models (DDPMs) to extract anatomical features. We train a DDPM on 21 unlabeled...

    arxiv.org/abs/2608.25693 · PDF

  13. 13

    A Dual-Transformer for Multi-Camera View Recommendation

    Josep Cabacas-Maso, Carles Ventura, Ismael Benito-Altamirano

    cs.CV · cs.AI

    Multi-camera systems are foundational to modern media production, and multi-camera editing is a critical task. This involves the proper selection of the appropriate camera view at each moment. In this paper, we propose a novel Dual-Transformer architecture with Cross-Attention that heavily outperformed the current SOTA models over the TVMCE dataset (TV Shows Multicamera Editing dataset). Our model decouples these tasks: (1) a dedicated...

    arxiv.org/abs/2608.25601 · PDF

  14. 14

    V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning

    Shulin Tian, Minglun Li, Yuhao Dong, Hao Ding, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu

    cs.CV · cs.AI

    Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can undermine an otherwise plausible response. We argue that this is a credit-assignment failure in multimodal post-training. Scalar outcome rewards indicate whether an answer is acceptable, but do not identify which visual facts are grounded, which reasoning steps are...

    arxiv.org/abs/2608.25580 · PDF

  15. 15

    MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations

    Jongsuk Kim, Qiyu Wu, Zhuoyuan Mao, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji

    cs.CV · cs.AI

    Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent studies mitigate this issue by augmenting training with synthetic hard negatives generated by a cascade of large language models and text-to-image models, which incurs substantial pipeline overhead. We instead propose MLLMCLIP, a heterogeneous distillation framework...

    arxiv.org/abs/2608.25575 · PDF

  16. 16

    CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression

    Haobo Xiong, Shaobo Liu, Kai Liu, Chongyang Ding

    cs.CV · cs.AI

    To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. However, existing methods typically insert fine-tuning modules independently into frozen backbones, lacking explicit mechanisms for cross-layer coordination. To address this limitation, we propose a novel framework named CrossMambaTuning, which integrates State Space...

    arxiv.org/abs/2608.25568 · PDF

  17. 17

    AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research

    Xintong Zhang, Xiaomeng Fan, Shilin Yan, Ekko He, Zicheng Liu, Zijian Zou, Guannan Zhang, Yuwei Wu, Zhi Gao, Hongwei Xue

    cs.CV · cs.AI

    Video deep research answers complex questions by jointly understanding video content and retrieving external knowledge from the open Web. However, diverse questions and videos require different tool-use strategies, and inappropriate tool calls can produce incorrect results. Uncertain grounding and retrieval also make unnecessary interactions costly and error-prone, increasing latency and reasoning errors. To address these challenges, we...

    arxiv.org/abs/2608.25559 · PDF

  18. 18

    CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifact

    Rana Muhammad Ahmed, Sabahat Abbas

    cs.CV · cs.LG

    A plant-health score can appear precise while resting on duplicated image families, a long-tailed label space, or a runtime file that was never evaluated. We present CropCop, a closed-set recognition system spanning 120 operational plant-health classes and an evidence chain from corpus reconstruction to direct execution of the final quantised artifact. Starting from 117,546 audited images, we rejected the inherited partition after confirming...

    arxiv.org/abs/2608.25539 · PDF

  19. 19

    Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming

    Lewis de Zoete Grundy, Chris McCarthy, Christopher Fluke

    cs.CV · cs.AI

    Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human action recognition rely either on sparse skeletal representations, which lack fine-grained motion cues, or dense optical flow, which can be computationally expensive for low-latency perception pipelines. In this paper, we propose PoseOFF, a...

    arxiv.org/abs/2608.25495 · PDF

  20. 20

    DeCO: Discriminative Evidence Composition for Fine-Grained Dataset Distillation

    Chuixuan Fan, Guang Li, Shijie Wang, Dongzhan Zhou, Baoli Sun, Takahiro Ogawa, Miki Haseyama, Zhihui Wang

    cs.CV · cs.AI

    Dataset distillation compresses a large training set into a compact synthetic set while preserving its downstream utility. However, existing methods primarily preserve global image statistics and may overlook the localized evidence essential for fine-grained visual classification (FGVC), such as object parts, subtle textures, and region-specific structures. We formulate fine-grained dataset distillation as budgeted discriminative-evidence...

    arxiv.org/abs/2608.25480 · PDF

  21. 21

    4DStreamCtrl: Interactive Video Generation with Online 4D Control

    Shiqian Li, Chenguo Lin, Zhiguang Liu, Yu Tang, Jiarong Ou, Rui Chen, Yixin Zhu

    cs.CV · cs.AI

    Generative video models now synthesize footage nearly indistinguishable from reality. Their promise as interactive tools hinges on fine-grained control of how objects and the camera move over time, yet each existing approach captures only part of this: camera-parameter methods steer the viewpoint but cannot move objects, 2D-trajectory methods act in the image plane and ignore depth and occlusion, and recent 3D methods add geometry but run...

    arxiv.org/abs/2608.25479 · PDF

  22. 22

    Automatic weld seam segmentation for industrial quality control: a comparison of RGB and polarimetric imaging with CNN and transformer architectures

    Simone Garbin, Leonardo Venturoso, Marco Todescato

    cs.CV · cs.AI

    Visual inspection of welded assemblies remains one of the least automated stages in many industrial production processes, still depending largely on the experience of human operators and thus subject to inter-operator variability; the manufacturing of special-purpose machinery cabins, the setting of this study, is one representative case. This work evaluates the feasibility of automatic weld seam segmentation from RGB and polarimetric...

    arxiv.org/abs/2608.25465 · PDF

  23. 23

    VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality

    Longteng Jiang, DanDan Zheng, Qianqian Qiao, Heng Huang, Huaye Wang, Yihang Bo, Bao Peng, Jingdong Chen, Jun Zhou, Xin Jin

    cs.CV · cs.AI

    We introduce VGA-BenchV2, an extended human-aligned benchmark and optimization framework for jointly evaluating and improving video generation quality and aesthetic value. Built upon VGA-Bench, VGA-BenchV2 preserves the original fine-grained taxonomy with two primary dimensions-Aesthetic and Generation-and 52 sub-dimensions. Guided by this taxonomy, we curate 1,016 diverse prompts and collect over 60,000 videos generated by 12 mainstream...

    arxiv.org/abs/2608.25452 · PDF

  24. 24

    Saliency-Depth Conditioning for Zero-Shot Segmentation of Communication-Tower Components in Cluttered UAV Imagery

    Ali Lesani, Chul Min Yeum, Su-Min Kang

    cs.CV · cs.AI · cs.RO

    Fine-grained segmentation of communication-tower components in UAV imagery is essential for automated inspection, yet task-specific models are hard to develop due to limited instance-level annotations. Zero-shot segmentation models offer a promising alternative, but in cluttered scenes, visually similar background structures interfere with component localization, causing missed instances and false positives. We propose a model-agnostic...

    arxiv.org/abs/2608.25435 · PDF

  25. 25

    PIVOT: A Multi-Trajectory Dataset and Testbed for Pose, Intrinsics, and Novel Viewpoint Evaluation in Real-World 3D Reconstruction

    Mary Raymond

    cs.CV · cs.AI

    Neural radiance fields (NeRFs), 3D Gaussian Splatting (3DGS), and related novel-view synthesis methods are commonly evaluated under capture and reconstruction conditions cleaner than those encountered by robots, drones, and autonomous systems. Benchmarks often rely on reconstruction-friendly trajectories, optimized camera poses and intrinsics, and held-out views sampled from trajectories represented during training. These assumptions can...

    arxiv.org/abs/2608.25401 · PDF

  26. 26

    CoRE: Weakly Supervised Coarse-to-Fine Risk Evidence Learning in Driving Videos

    Kaiser Hamid, Can Cui, Nade Liang

    cs.CV · cs.AI

    Perceived risk in driving evolves over time and may be supported by specific scene entities, yet supervision is typically limited to coarse video-level judgments. Learning \emph{when} supporting evidence emerges and \emph{which entities} support a risk predictor would ordinarily require costly temporal- and entity-level annotations. We introduce \textbf{CoRE}, a weakly supervised coarse-to-fine framework that learns fine-grained prediction...

    arxiv.org/abs/2608.25344 · PDF

  27. 27

    WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution

    Tayyab Nasir, Daochang Liu, Ajmal Mian

    cs.CV · cs.LG

    Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. Thus, low-level spatial cues surface in early layers, leaving the deeper layers to suppress those that do not correspond to true depth boundaries, which risks artifacts and blurred edges. The same fine-to-coarse bias persists in semantics-based methods that consume low-level tokens early and...

    arxiv.org/abs/2608.25302 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.