arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Computer Vision · 会议 · Computer Vision

共收录 4770
2509.06803 2025-09-09 cs.CV

MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration

George Ciubotariu, Zhuyun Zhou, Zongwei Wu, Radu Timofte

机构 * Computer Vision Lab, CAIDAS & IFI, University of Würzburg(计算机视觉实验室、CAIDAS与IFI、乌尔姆大学)

Comments ICCV 2025 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.06485 2025-09-09 cs.CV

WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting

Andrea Marelli, Alberto Foresti, Leonardo Pesce, Giacomo Boracchi, Mario Grosso

机构 * Politecnico di Milano(米兰理工大学) EURECOM

Comments 10 pages, 7 figures, ICCV 2025 - Workshops The WS$^2$ dataset is publicly available for download at https://zenodo.org/records/14793518, all the details are reported in the supplementary material

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.06413 2025-09-09 cs.CV eess.IV

VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results

Yixiao Li, Xin Li, Chris Wei Zhou, Shuo Xing, Hadi Amirpour, Xiaoshuai Hao, Guanghui Yue, Baoquan Zhao, Weide Liu, Xiaoyuan Yang, Zhengzhong Tu, Xinyu Li, Chuanbiao Song, Chenqi Zhang, Jun Lan, Huijia Zhu, Weiqiang Wang, Xiaoyan Sun, Shishun Tian, Dongyang Yan, Weixia Zhang, Junlin Chen, Wei Sun, Zhihua Wang, Zhuohang Shi, Zhizun Luo, Hang Ouyang, Tianxin Xiao, Fan Yang, Zhaowang Wu, Kaixin Deng

机构 * Yixiao Li(* 李夕宵) Xin Li(* 李鑫) Chris Wei Zhou(* 周克里斯) Shuo Xing(* 熊朔) Hadi Amirpour(* 阿米尔普尔) Xiaoshuai Hao(* 郝晓帅) Guanghui Yue(* 袁广会) Baoquan Zhao(* 赵宝全) Weide Liu(* 刘伟德) Xiaoyuan Yang(* 杨晓元) Zhengzhong Tu(* 途正忠) Xinyu Li(* 李新宇) Chuanbiao Song(* 宋传标) Chenqi Zhang(* 张晨琪) Jun Lan(* 兰俊) Huijia Zhu(* 朱会佳) Weiqiang Wang(* 王伟强) Xiaoyan Sun(* 孙晓燕) Shishun Tian(* 天世顺) Dongyang Yan(* 严东阳) Weixia Zhang(* 张伟霞) Junlin Chen(* 陈军林) Wei Sun(* 孙伟) Zhihua Wang(* 王志强) Zhuohang Shi(* 史卓hang) Zhizun Luo(* 罗志军) Hang Ouyang(* 欧hang) Tianxin Xiao(* 肖天心) Fan Yang(* 杨帆) Zhaowang Wu(* 吴昭王) Kaixin Deng(* 邓凯欣)

Comments 11 pages, 12 figures, VQualA ICCV Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05975 2025-09-09 cs.CV cs.AI

ConstStyle: Robust Domain Generalization with Unified Style Transformation

Nam Duong Tran, Nam Nguyen Phuong, Hieu H. Pham, Phi Le Nguyen, My T. Thai

机构 * Institute for AI Innovation and Societal Impact, Hanoi University of Science and Technology(人工智能创新与社会影响研究所,河内科学技术大学) VinUniversity(文大学) University of Florida(佛罗里达大学)

Comments Accepted at ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12543 2025-09-09 cs.CV

REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language

Ipsita Praharaj, Yukta Butala, Badrikanath Praharaj, Yash Butala

机构 * Carnegie Mellon University(卡内基梅隆大学) VIT Bhopal(维捷商学院)

Comments 4 pages, 6 figures, International Conference on Computer Vision, ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09632 2025-09-09 cs.CV cs.AI

Preacher: Paper-to-Video Agentic System

Jingwei Liu, Ling Yang, Hao Luo, Fan Wang, Hongyan Li, Mengdi Wang

机构 * School of Intelligence Science and Technology, Peking University(北京理工大学智能科学与技术学院) DAMO Academy, Alibaba group(阿里巴巴集团大模型研究院) Hupan Lab(虎扑实验室) National Key Laboratory of General Artificial Intelligence, Peking University(北京人工智能 general artificial intelligence 国家重点实验室) Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系)

Comments ICCV 2025. Code: https://github.com/Gen-Verse/Paper2Video

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13111 2025-09-09 cs.CV cs.CL cs.LG

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

Erik Daxberger, Nina Wenzel, David Griffiths, Haiming Gang, Justin Lazarow, Gefen Kohavi, Kai Kang, Marcin Eichner, Yinfei Yang, Afshin Dehghan, Peter Grasch

机构 * Apple(苹果公司)

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.08334 2025-09-09 cs.CV

LD-SDM: Language-Driven Hierarchical Species Distribution Modeling

Srikumar Sastry, Xin Xing, Aayush Dhakal, Subash Khanal, Adeel Ahmad, Nathan Jacobs

机构 * Washington University in St. Louis(圣路易斯华盛顿大学) University of Nebraska Omaha(内布拉斯加大学奥马哈分校)

Comments Accepted at Computer Vision for Ecology (CV4E) Workshop, ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05543 2025-09-09 cs.CV

DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation

Haitao Tian, Pierre Payeur

机构 * University of Ottawa(渥太华大学)

Comments ICCV 2025 accepted paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03864 2025-09-09 cs.AI

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

Zhenyu Pan, Yiting Zhang, Yutong Zhang, Jianshu Zhang, Haozheng Luo, Yuwei Han, Dennis Wu, Hong-Yu Chen, Philip S. Yu, Manling Li, Han Liu

机构 * Northwestern University(西北大学) University of Illinois at Chicago(伊利诺伊大学香槟分校)

Comments accepted by the Trustworthy FMs workshop in ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23067 2025-09-09 cs.AI

FairReason: Balancing Reasoning and Social Bias in MLLMs

Zhenyu Pan, Yutong Zhang, Jianshu Zhang, Haoran Lu, Haozheng Luo, Yuwei Han, Philip S. Yu, Manling Li, Han Liu

机构 * Northwestern University(西北大学) University of Illinois at Chicago(伊利诺伊大学香槟分校)

Comments Accepted to the Trustworthy FMs workshop in ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05297 2025-09-08 cs.CV

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

Matteo Poggi, Fabio Tosi

机构 * Department of Computer Science and Engineering (DISI)(计算机科学与工程系) Advanced Research Center on Electronic System (ARCES)(电子系统高级研究中心) University of Bologna(博洛尼亚大学)

Comments ICCV 2025 - Project Page: https://flowseek25.github.io/ - Code: https://github.com/mattpoggi/flowseek

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05092 2025-09-08 cs.CV

Semi-supervised Deep Transfer for Regression without Domain Alignment

Mainak Biswas, Ambedkar Dukkipati, Devarajan Sridharan

机构 * Brain, Computation and Data Sciences(脑科学与数据科学) Centre for Neuroscience(神经科学中心) Computer Science and Automation(计算机科学与自动化)

Comments 15 pages, 6 figures, International Conference on Computer Vision 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05086 2025-09-08 cs.CV cs.LG

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers

Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit, J. Marius Zöllner

机构 * Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院) FZI Research Center for Information Technology(弗劳恩霍夫信息与通信技术研究中心)

Comments Accepted for publication at the STREAM workshop at ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23567 2025-09-08 cs.CV

3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Yung-Hsu Yang, Luigi Piccinelli, Mattia Segu, Siyuan Li, Rui Huang, Yuqian Fu, Marc Pollefeys, Hermann Blum, Zuria Bauer

机构 * ETH Zürich(苏黎世联邦理工学院) Tsinghua University(清华大学) INSAIT, Sofia University(INSAIT,索菲亚大学) Microsoft(微软) University of Bonn(波恩大学)

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20309 2025-09-08 cs.CV

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs

Zitian Wang, Yue Liao, Kang Rong, Fengyun Rao, Yibo Yang, Si Liu

机构 * Beihang University(北航大学) National University of Singapore(国立新加坡大学) King Abdullah University of Science and Technology(国王 Abdullah 科学与技术大学)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19065 2025-09-08 cs.CV

WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation

Zhongyu Yang, Jun Chen, Dannong Xu, Junjie Fei, Xiaoqian Shen, Liangbing Zhao, Chun-Mei Feng, Mohamed Elhoseiny

机构 * King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹大学科学与技术大学) Lanzhou University(兰州大学) Meta AI The University of Sydney(悉尼大学) IHPC, A*STAR(IHPC,A*STAR)

Comments ICCV 2025, Project in https://wikiautogen.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.04631 2025-09-08 cs.CV

Disentangled Clothed Avatar Generation with Layered Representation

Weitian Zhang, Yichao Yan, Sijing Wu, Manwen Liao, Xiaokang Yang

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(人工智能教育部重点实验室、人工智能研究院、上海交通大学) The University of Hong Kong(香港大学)

Comments ICCV 2025 highlight, project page: https://olivia23333.github.io/LayerAvatar/

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17784 2025-09-08 cs.CV

HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

Lingxiao Li, Kaixuan Fan, Boqing Gong, Xiangyu Yue

机构 * MMLab, The Chinese University of Hong Kong(香港中文大学) Boston University(波士顿大学)

Comments ICCV 2025, Code is available at: https://github.com/lingxiao-li/HypDAE

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.17422 2025-09-08 cs.RO cs.CV

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

Wen Jiang, Boshu Lei, Katrina Ashton, Kostas Daniilidis

机构 * University of Pennsylvania(宾夕法尼亚大学) Archimedes, Athena RC(阿基米德、阿提卡RC)

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
1912.04134 2025-09-08 eess.IV cs.CV

Estimation of Muscle Fascicle Orientation in Ultrasonic Images

Regina Pohle-Fröhlich, Christoph Dalitz, Charlotte Richter, Benjamin Stäudle, Kirsten Albracht

机构 * Institute for Pattern Recognition, Niederrhein University of Applied Sciences(模式识别研究所,南莱茵应用科学大学) Institute of Biomechanics and Orthopaedics, German Sport University Cologne(生物力学与骨科研究所,德国体育大学科隆)

Comments 7 pages, 7 figures, accepted for VISAPP 2020

Journal ref International Conference on Computer Vision Theory and Applications (VISAPP), pp. 79-86 (2020)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04669 2025-09-08 cs.CV cs.AI cs.LG

VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation

Mustafa Munir, Alex Zhang, Radu Marculescu

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Comments Proceedings of the 2025 IEEE/CVF International Conference on Computer Vision (ICCV) Workshops

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04582 2025-09-08 cs.CV

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

Jingyi Lu, Kai Han

机构 * Visual AI Lab, The University of Hong Kong(视觉人工智能实验室,香港大学)

Comments Accepted to ICCV 2025. Project page: https://visual-ai.github.io/inpaint4drag/

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06269 2025-09-08 cs.CV cs.AI

BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields

Rushil Desai

机构 * Berkeley Artificial Intelligence Research(伯克利人工智能研究)

Comments ICCV 2025 Workshops (11 Pages, 6 Figures, 2 Tables)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03895 2025-09-05 cs.CV

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model

Phuoc-Nguyen Bui, Khanh-Binh Nguyen, Hyunseung Choo

机构 * Sungkyunkwan University(顺天大学) Deakin University(德金大学)

Comments ICCV 2025 - LIMIT Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03893 2025-09-05 cs.CV

Weakly-Supervised Learning of Dense Functional Correspondences

Stefan Stojanov, Linan Zhao, Yunzhi Zhang, Daniel L. K. Yamins, Jiajun Wu

机构 * Stanford University(斯坦福大学)

Comments Accepted at ICCV 2025. Project website: https://dense-functional-correspondence.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03609 2025-09-05 cs.CV

Towards Efficient General Feature Prediction in Masked Skeleton Modeling

Shengkai Sun, Zefan Zhang, Jianfeng Dong, Zhiyong Cheng, Xiaojun Chang, Meng Wang

机构 * Hefei University of Technology(合肥工业大学) Jilin University(吉林大学) Zhejiang Gongshang University(浙江工商大学) University of Science and Technology of China(中国科学技术大学)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03501 2025-09-04 cs.CV cs.AI cs.HC cs.LG

Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data

Honglu Zhou, Xiangyu Peng, Shrikant Kendre, Michael S. Ryoo, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles

机构 * Salesforce AI Research(Salesforce AI研究院)

Comments This technical report serves as the archival version of our paper accepted at the ICCV 2025 Workshop. For more information, please visit our project website: https://strefer.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03465 2025-09-04 cs.CV

Joint Training of Image Generator and Detector for Road Defect Detection

Kuan-Chuan Peng

机构 * Mitsubishi Electric Research Laboratories (MERL)(三菱电机研究实验室)

Comments This paper is accepted to ICCV 2025 Workshop on Representation Learning with Very Limited Resources: When Data, Modalities, Labels, and Computing Resources are Scarce as an oral paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03385 2025-09-04 cs.CV

Human Preference-Aligned Concept Customization Benchmark via Decomposed Evaluation

Reina Ishikawa, Ryo Fujii, Hideo Saito, Ryo Hachiuma

机构 * Keio University(庆应大学) NVIDIA(英伟达)

Comments Accepted to ICCV Workshop 2025

详情

展开后加载摘要…

URL PDF HTML 收藏