cs.CV · 2026-10-10 · No. 139

Computer Vision and Pattern Recognition, 2026-10-10.

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

01 — The papers

24 entries
  1. 01

    One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

    Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos

    cs.CV · cs.LG

    In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank. A continuous normalized-depth coordinate programs this mixture, defining a resampleable...

    arxiv.org/abs/2610.12448 · PDF

  2. 02

    Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

    Luping Liu, Bingyi Kang, Yifan Wang, Dong Xu

    cs.CV · cs.LG

    Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-guided generation (IEG), where transformations can preserve visual identity while breaking physical continuity. To establish identity-preserving correspondence across such transformations, we introduce...

    arxiv.org/abs/2610.12421 · PDF

  3. 03

    WOVEN: Weaving Visual World Modeling into Multimodal LLMs

    Zheyu Fan, Yue Zhang, Mingkai Deng, Kangrui Wang, Qineng Wang, Canyu Chen, Jie Hao, Xing Fan, Chenlei Guo, Eric P....

    cs.CV · cs.CL · cs.LG

    Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, and test whether this capability can serve as a shared training primitive, one that different models can learn from different supervision sources and reuse across different tasks, with a systematic training recipe. Existing benchmarks document...

    arxiv.org/abs/2610.12417 · PDF

  4. 04

    MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances

    Mingyuan Lei, Yoonchang Sung, Tat-Jen Cham

    cs.CV · cs.AI

    Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion. However, supervision for these capabilities is rarely available jointly at scale. Human-scene datasets provide rich information about environment-aware motion, while human-object datasets capture detailed interaction...

    arxiv.org/abs/2610.12416 · PDF

  5. 05

    SpaceFlow: Locally Controllable 3D Generation

    Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov, Felicia Scharitzer, Marc Pollefeys, Ata Celen, Sayan Deb...

    cs.CV · cs.AI · cs.GR

    Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present SpaceFlow, a training-free pipeline for locally controllable 3D generation from text descriptions and a collection of geometric primitives. Each primitive serves as a proxy for an object part and is assigned a local control level, enabling users to specify whether...

    arxiv.org/abs/2610.12399 · PDF

  6. 06

    Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models

    Hongxing Li, Yixin Li, Dingming Li, Zixuan Wang, Yuchen Yan, Wenqi Zhang, Weiming Lu, Yongliang Shen

    cs.CV · cs.AI

    Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies either inject 3D into the model at inference, paying architecture and latency costs, or train with outcome rewards that supervise only the final answer. Spatial errors originate in perception: a misjudged depth or direction can be corrected only by the scene's true geometry, which...

    arxiv.org/abs/2610.12355 · PDF

  7. 07

    ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration

    Jialei He, Enhe Liu, Sifan Song, Pengfei Jin, Jionglong Su, Hongbin Wang, Zhixiang Lu, Yanhao Huang, Anteng Cai,...

    cs.CV · cs.AI

    Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variations in slice sampling. We introduce ContiLNN, which augments two-dimensional restoration backbones with bidirectional closed-form continuous-time (Bi-CfC) modules for cross-slice modeling while retaining in-plane feature extraction. Slice-index intervals modulate gates determined by local...

    arxiv.org/abs/2610.12337 · PDF

  8. 08

    RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning

    Ruixiang Ouyang, Guanren Qiao, Fansen Meng, Yueci Deng, Ruixing Jin, Kui Jia, Guiliang Liu

    cs.CV · cs.AI · cs.GR · cs.LG

    Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local contacts between surfaces shape object motion remains challenging. While end-to-end world models predict interactions across entire scenes or objects, in practice, rigid-body contact is inherently local, and only nearby surfaces can directly exchange contact forces....

    arxiv.org/abs/2610.12333 · PDF

  9. 09

    Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

    Dahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim

    cs.CV · cs.AI

    Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents that act and interact within a shared environment. Existing multi-agent world models rely on coarse actions like locomotion, camera control, or discrete commands, leaving fine-grained embodied interactions underexplored. We formulate multi-agent egocentric world...

    arxiv.org/abs/2610.12299 · PDF

  10. 10

    DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception

    Jinghua Hou, Zhe Liu, Hengshuang Zhao

    cs.CV · cs.AI

    Multimodal large language models have made remarkable progress in bridging vision and language, facilitating various perception tasks essential for human-machine interaction, robotics, and autonomous driving. However, existing MLLM-based perception methods predominantly rely on text-based coordinate representation, which suffers from excessive token overhead, or fixed-range quantization, which suffers from range and precision constraints,...

    arxiv.org/abs/2610.12266 · PDF

  11. 11

    Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings

    Youngtaek Oh, Qiyu Wu, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji

    cs.CV · cs.AI · cs.IR

    Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal embedding methods often rely on a single shared parameter space over mixed-modality data, limiting structural separation between universal and modality-specific representations. To address this, we propose Syn-Omni, a unified framework for structured omnimodal adaptation with modality...

    arxiv.org/abs/2610.12256 · PDF

  12. 12

    From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

    Yitong Wang, Fangyun Wei, Jinjing Zhao, Sirui Zhang, Hongyang Zhang, Dong Chen, Bo Dai, Yan Lu

    cs.CV · cs.AI

    Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of words. We introduce a Spatial Canvas Interface that enables users to directly compose generation intent in space through four complementary binding types: semantic, identity, text, and pixel, together with Text Specifications for individual elements and global appearance....

    arxiv.org/abs/2610.12230 · PDF

  13. 13

    VibeEdit: Image Editing with Canvas Instructions

    Jinjing Zhao, Fangyun Wei, Yitong Wang, Xiuyu Wu, Yunuo Chen, Yang Yue, Sirui Zhang, Wenbo Wang, Hongyang Zhang,...

    cs.CV · cs.AI

    In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when several objects look alike. We introduce a new image editing interface that lets users place spatial marks and optional short notes directly on the image. Together, these annotations form a canvas instruction that specifies where to edit and what to change. Our editor, VibeEdit,...

    arxiv.org/abs/2610.12229 · PDF

  14. 14

    AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware

    Thomas Goudemant, Aurélien Bobey, Omar Hlimi, Marjorie Bellizzi

    cs.CV · cs.AI

    Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover a tiny fraction of each scene. We study onboard vessel detection as a way to select what is downlinked, which reduces the data according to its content rather than coding every pixel; it is complementary to conventional onboard compression. The work follows three axes. (i) Data and algorithm: a...

    arxiv.org/abs/2610.12182 · PDF

  15. 15

    LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views

    Qizhou Huo, Xuan Sun, Yongfei Guo, Zhipeng Wang, Yuanhao Gong

    cs.CV · cs.AI · cs.GR · cs.MM · eess.IV

    Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaussian Splatting nevertheless renders each target view, leaving this image overlap unexploited. Reusing rendered images offers an alternative. Geometric warping alone cannot recover newly exposed content and remains sensitive to depth errors. We propose a per-scene framework that replaces repeated...

    arxiv.org/abs/2610.12127 · PDF

  16. 16

    VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling

    Leigang Qu, Feng Cheng, Ziyan Yang, Bangbang Yang, Zhaoyang Huang, Wei Chow, Yicong Li, Wenjie Wang, Tat-Seng Chua, Yan Zeng

    cs.CV · cs.AI · cs.MM

    Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are prohibitively expensive to annotate and difficult to synthesize at scale, whereas image editing has already reached maturity with millions of such pairs readily available. In this work, we introduce VINCIE-NExT, a unified framework that transfers editing capability from images to videos through...

    arxiv.org/abs/2610.12104 · PDF

  17. 17

    DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning

    Wenhao Li, Xianjing Meng, Qiangchang Wang, Zhongyi Han, Yilong Yin, Liqiang Nie

    cs.CV · cs.LG

    Few-shot learning aims to recognize novel categories from limited labeled examples. Recent studies incorporate textual semantics to compensate for limited visual observations and improve class representations. However, high image-text agreement may reflect both intrinsic object properties and incidental context, making support prototypes susceptible to contextual contamination. To address this problem, we propose DVLA-RL++, which extends...

    arxiv.org/abs/2610.12095 · PDF

  18. 18

    Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning

    Fedor Kitashov, João Carreira, Shiry Ginosar, Dima Damen, Andrew Zisserman, Viorica Pătrăucean

    cs.CV · cs.LG

    Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026 in Malmö, Sweden. This edition focused on spatial intelligence and featured four different tracks: unified multiple-choice videoQA and grounded videoQA from the original Perception Test benchmark, alongside two new tracks based on city-scale walking-tour videos (KilometerAudio and...

    arxiv.org/abs/2610.12081 · PDF

  19. 19

    DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

    Yupeng Xie, Zhenyang Wang, Jiayi Zhu, Yinghao Tang, Zhouan Shen, Yiyu Chen, Yuyu Luo

    cs.CV · cs.AI · cs.CL

    Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video understanding, data video understanding places greater emphasis on accurately reading data from animated charts, integrating evidence across charts and time, and understanding how narrative organization and visual design communicate information. Yet existing benchmarks target...

    arxiv.org/abs/2610.11993 · PDF

  20. 20

    Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows

    Jierui Lei, Wenjian Zhang, Qingyi Yang, Yuyang Hong, Fangzheng Chen, Zhengbo Zhang, Haina Tang, Shiming Xiang

    cs.CV · cs.LG

    Media-bridged time series forecasting is expanding to encompass traditional "multivariate" and emerging "multimodal" (e.g., through textual assistance). Existing Time Series Forecasting (TSF) models still rely on paradigm-specific relation, fusion, and temporal modules, hindering a common forecasting backbone across numerical and pre-aligned narrative-flow settings. To explore this, we propose the Multimedia Identity-Aware Prism Network...

    arxiv.org/abs/2610.11924 · PDF

  21. 21

    Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations

    Shuran Ma, JiaLe Li, Yuxin Dong, Shan Zheng, Qingyun Jiang, Xiang Chen, Qi Zhu, Deyi Ji, Yifan Yang, Jianfeng Pan,...

    cs.CV · cs.AI

    Hallucination remains a significant challenge in Large Vision-Language Models (LVLMs). Existing training-free methods generally mitigate hallucinations through contrastive decoding or visual enhancement, often increasing the relative influence of visual evidence during generation. This raises a fundamental question: Can LVLMs dynamically regulate the contributions of different context sources to suppress hallucinations? In this work, we...

    arxiv.org/abs/2610.11907 · PDF

  22. 22

    Open-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusion

    Anirudh Praveen, Koteswar Rao Jerripothula, Pratik Joshi, Aveen Dayal, Neela Sawant

    cs.CV · cs.LG · cs.MM · cs.SD · eess.IV

    Open-Vocabulary Audio-Visual Event Localization (OV-AVEL) labels each video segment with an event class, including classes that were never seen during training. The dominant pipeline uses a frozen multimodal foundation model (e.g. ImageBind) to embed the visual frame, the audio mel-spectrogram, and each candidate class name into a shared space, then computes two cosine similarities for each segment against each class: visual-text and...

    arxiv.org/abs/2610.11846 · PDF

  23. 23

    From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment

    Chen Zhao, Xingping Dong, Jiachun Shi, Liang Peng, Chong Wang, Zhen Lei, Ran He, Bo Du

    cs.CV · cs.AI

    Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content. An intuitive mitigation strategy is to suppress hallucination-related components in hidden representations. However, these components may also contain useful information, and suppressing them can weaken the model's multimodal capabilities. In this paper, we propose ResOT, a training-free method that repairs representations at...

    arxiv.org/abs/2610.11826 · PDF

  24. 24

    From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction

    Uddipan Basu Bir, Vincent Christlein, Andreas Maier, Mathias Zinnen

    cs.CV · cs.AI

    While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limits adoption in institutional archives due to data autonomy concerns, recurring costs, and the environmental footprint of hyperscale computing. This is especially acute in heritage digitization, where documents include historical handwriting, domain-specific terminology (e.g., jewelry, prehistory,...

    arxiv.org/abs/2610.11818 · 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.