cs.CV · 2026-07-27 · No. 66

Computer Vision and Pattern Recognition, 2026-07-27.

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

01 — The papers

22 entries
  1. 01

    SM4RT: Learning Structured Motion Geometry for 4D Reconstruction

    Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo, Yuqi Wu, Jie Zhou, Jiwen Lu

    cs.CV · cs.AI · cs.RO

    Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding remains a fundamental challenge. Most existing motion perception methods (e.g., sparse tracking, dense point-wise flow) treat motion as independent point-wise displacements, ignoring the structured nature of physical motion. However, real-world objects usually obey rigid-body kinematics, and...

    arxiv.org/abs/2607.22534 · PDF

  2. 02

    SiPhy: Single-Image Physical Property Reasoning

    Hoang Le, Joonwoo Kwon, Elkhan Ismayilzada, Yufei Zhang, Zijun Cui

    cs.CV · cs.AI

    Inferring physical properties such as mass, stiffness, and elasticity from a single image is essential for simulation and embodied AI, yet most existing approaches rely on multi-view reconstruction or physics-based supervision. We introduce SiPhy, a unified framework for single-image physical property reasoning that aligns 3D-aware visual cues, depth with language-based material knowledge. From one RGB image, SiPhy samples pseudo-voxel...

    arxiv.org/abs/2607.22355 · PDF

  3. 03

    Time-Reversed Imaging: A Multimodal Benchmark and Framework for Reconstructing Past Human-Environment Interactions

    Jorge Bacca, Kebin Contreras, Luis Toscano-Palomino, Mauro Dalla Mura

    cs.CV · cs.AI · eess.IV

    We introduce time-reversed imaging, a new paradigm that infers what just happened in a scene from fading multimodal traces. Instead of extrapolating or interpolating video frames, our goal is to infer past human-environment interactions from residual physical imprints observable in thermal, ultraviolet, and visible spectra. To study this problem, we present TRACE-HEI, the first proof-of-concept dataset for time-reversed imaging, containing...

    arxiv.org/abs/2607.22352 · PDF

  4. 04

    TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution

    Sicheng Gao, Zhuyun Zhou, Yixuan Liu, Tong Shen, Zongwei Wu, Radu Timofte

    cs.CV · cs.AI

    Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due to the quadratic computational cost of processing dense spatio-temporal token sequences. Existing efficiency-oriented methods risk irreversible detail loss and temporal flickering, a vulnerability especially pronounced in one-step diffusion models. To address this, we propose TRaM-VSR, a Token...

    arxiv.org/abs/2607.22231 · PDF

  5. 05

    Deep Convolutional Large-Margin $\ell_p$-SVDD for Visual Anomaly Detection

    Alireza Dastmalchi Saei, Shervin Rahimzadeh Arashloo

    cs.CV · cs.LG

    Visual anomaly detection requires adaptive representations and reliable decision boundaries, particularly when anomalous training samples are scarce and class distributions are highly imbalanced. Classical kernel-based methods yield principled geometric decision regions but typically operate on fixed features, while deep detectors learn task-specific representations but often fail to provide an explicit margin-aware kernel boundary. In this...

    arxiv.org/abs/2607.22212 · PDF

  6. 06

    Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs

    Yuheng Zong, Minghua Wang, Xin Zhao, Zhi-Hui Zhan, Antonio Plaza, Jon Atli Benediktsson

    cs.CV · cs.AI

    Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications require fine-grained scenario specialization, constrained by scarce high-quality scenario data and incomplete capability coverage. We formulate this adaptation as a capability-gap-driven post-training problem and propose filling before advancing (FBA). Rather than relying on single-stage...

    arxiv.org/abs/2607.22205 · PDF

  7. 07

    Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning

    Moritz Vandenhirtz, Andrea Agostini, Dana Belde, Mélanie Roschewitz, Ismaiel Chikh Bakri, Tilo Niemann, André Euler,...

    cs.CV · cs.LG

    Bowel obstruction is a common and potentially life-threatening gastrointestinal condition. In the face of rising diagnostic workloads, the automated diagnosis of bowel obstruction on CT scans supports radiologists by accelerating detection and improving patient outcomes. In this work, we propose a deep learning framework with a multi-task objective that jointly detects bowel obstruction and localizes its transition zone. Additionally, we...

    arxiv.org/abs/2607.22173 · PDF

  8. 08

    dRAE: Representation Autoencoder with Hyper-Spherical Codes

    Tianren Ma, Lin Long, Chuyan Chen, Mu Zhang, Junbo Zhao, Tong Zhang, Qixiang Ye

    cs.CV · cs.AI

    In this work, we aim to discretize the high-dimensional visual representations to bridge the gap with language models - a non-trivial challenge, as existing quantization methods suffer from codebook collapse, failing to scale while preserving semantic coherence. We identify the root cause as metric mismatch: standard Euclidean codebook objectives are fundamentally misaligned with the anisotropic geometry of representation space, leading to...

    arxiv.org/abs/2607.22148 · PDF

  9. 09

    CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography

    Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut, Adam Brzeski, Tomasz Dziubich, Radosław Targoński, Tomasz...

    cs.CV · cs.AI · cs.LG

    Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols. In this work we demonstrate a new benchmark for the assessment of deep learning models which densely classify pixels of coronary angiograms to one of SYNTAX classes (or background). The evaluation covers 24 distinct architectures starting with classic convnets to recent...

    arxiv.org/abs/2607.22139 · PDF

  10. 10

    Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

    Yu Wang, Hongyu Yang

    cs.CV · cs.LG

    Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations. In this work, we revisit this assumption in the foundation-model era through a comprehensive empirical study. A single DINOv3-pretrained ConvNeXt trained with a tuned recipe achieves 88.19 mAP on VeRi-Wild Small and 77.47 mAP on VeRi-Wild Large using visual...

    arxiv.org/abs/2607.22068 · PDF

  11. 11

    Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

    M M Asif Ferdous

    cs.CV · cs.CL · cs.LG

    Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at...

    arxiv.org/abs/2607.22034 · PDF

  12. 12

    EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection

    Hao Yang, Jin Wang, Xuejie Zhang

    cs.CV · cs.AI

    MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a joint interpretation of text and vision. Existing methods focus on the dual-stream vision-language model to extract the visual and text simultaneously, which lacks background information and prior knowledge about the comprehensive explanation of MEME. One feasible option is to adopt...

    arxiv.org/abs/2607.22016 · PDF

  13. 13

    Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning

    Hao Yang, Jin Wang, Xuejie Zhang

    cs.CV · cs.AI

    Multimodal chain-of-thought (CoT) reasoning integrates visual and textual cues through step-by-step inference. In small models with limited token budgets, modality-interaction fusion often suppresses tiny cross-modal differences. In particular, multimodal CoT often struggles when different images pair with identical text or different texts pair with an identical image, making such inputs nearly indistinguishable after fusion. This study...

    arxiv.org/abs/2607.22013 · PDF

  14. 14

    TextSLIP: Text Self-Supervised CLIP for Medical Report Generation

    Haoyu Jiang, Ziping Cong

    cs.CV · cs.AI

    Automating radiology report generation is important for improving reporting consistency and clinical workflows . While Contrastive Language--Image Pretraining (CLIP) has advanced medical vision language modeling, existing CLIP-style approaches may still provide insufficient fine-grained semantic supervision for complex report generation. Standard CLIP primarily optimizes cross-modal alignment, without explicitly structuring the textual...

    arxiv.org/abs/2607.21970 · PDF

  15. 15

    ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors

    Jiale Zhao, Jiajun Wan, Lei Tang, Ye Qin, Kebing Jin, Jinghui Qin

    cs.CV · cs.AI · cs.CR

    The rapid advancement of generative models has spurred the critical need to evaluate the worst-case robustness of deepfake detectors. In this paper, we reveal a fundamental blind spot in current forensic paradigms: while existing detectors excel at capturing digital synthesis artifacts, their effectiveness drops drastically when AI-generated content is cloaked in authentic physical imaging characteristics. We posit that genuine photographs...

    arxiv.org/abs/2607.21897 · PDF

  16. 16

    Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement

    Mohammadreza Narimani, Vikram Anand, Parastoo Farajpoor

    cs.CV · cs.LG · eess.IV

    Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis. This study presents a reproducible workflow for mapping farmland extent and visible boundaries from 1 m NAIP RGB imagery. Thirty-seven scenes spanning open cropland, peri-urban interfaces, semi-arid irrigation geometries, and fragmented mosaics were annotated...

    arxiv.org/abs/2607.21881 · PDF

  17. 17

    SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes

    Chia-Tung Ho, Haoyu Yang, Guanglei Zhou, Yoshi Nishi, Yaguang Li, Walker Turner, Cunxi Yu, Yiran Chen, Brucek Khailany

    cs.CV · cs.AI

    As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by complex rule interactions, dense multi-layer routing geometries, and foundry-specific constraints. While Large Language Models (LLMs) have recently demonstrated strong capabilities in EDA scripting and documentation, their application to visual layout understanding remains largely unexplored:...

    arxiv.org/abs/2607.21850 · PDF

  18. 18

    3D-Aware VLMs with Implicit and Explicit Geometries

    Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang

    cs.CV · cs.AI · cs.LG

    Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified framework that enhances the 3D spatial awareness of VLMs by equipping them with both implicit and explicit 3D geometries learned from RGB videos. Our VLM-IE3D introduces Implicit Geometry...

    arxiv.org/abs/2607.21595 · PDF

  19. 19

    GraphVid: Interactive Graph-Controllable Video Generation

    Vedant Shah, Onkar Susladkar, Tushar Prakash, Kiet Nguyen, Tianjio Yu, Adheesh Juvekar, Muntasir Waheed, Ismini Lourentzou

    cs.CV · cs.AI

    Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject...

    arxiv.org/abs/2607.21580 · PDF

  20. 20

    Synthetic data generation framework for quality control automation in gravure printing

    Korota Arsène Coulibaly, Mohamed Hamlich, Khalid Hmali, Andrea Trombin

    cs.CV · cs.AI · cs.LG · eess.IV

    Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards in rotogravure printing. Deep learning models give prospects for automation. However, training robust deep learning models, such as YOLO or Vision Transformers, is heavily hindered by the extreme scarcity of real-world...

    arxiv.org/abs/2607.21577 · PDF

  21. 21

    Visual Contrastive Self-Distillation

    Yijun Liang, Yunjie Tian, Yijiang Li, Yuqi Jia, Furong Huang, Tianyi Zhou, Di Fu

    cs.CV · cs.AI

    On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods create this asymmetry either through privileged answers or visual evidence. We ask whether both can be removed, yielding a simpler form of OPSD...

    arxiv.org/abs/2607.21556 · PDF

  22. 22

    ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

    Yueyi Liu, Chi Zhang, Sen Cui, Miao Liu

    cs.CV · cs.AI

    Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational mismatch between the distribution-mapping nature of generative models and the single-point optimization of standard TTT. In this paper, we demonstrate that this mismatch triggers \textit{Prior Collapse}, a degenerate state where the model discards the text conditions and spatial latents, collapsing...

    arxiv.org/abs/2607.21529 · 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.