CVPR - arXivDaily 期刊&会议

2510.11204 2025-10-14 cs.CV

Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos

Rohit Gupta, Anirban Roy, Claire Christensen, Sujeong Kim, Sarah Gerard, Madeline Cincebeaux, Ajay Divakaran, Todd Grindal, Mubarak Shah

机构 * Center for Research in Computer Vision, University of Central Florida（计算机视觉研究中心，中央佛罗里达大学）； SRI International（SRI国际）

Comments Published at CVPR 2023

2510.10011 2025-10-14 cs.CV

MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output

Yanyuan Chen, Dexuan Xu, Yu Huang, Songkun Zhan, Hanpin Wang, Dongxue Chen, Xueping Wang, Meikang Qiu, Hang Li

机构 * School of Software & Microelectronics, Peking University（软件与微电子学院，北京大学）； School of Computer Science, Peking University（计算机学院，北京大学）； National Engineering Research Center for Software Engineering, Peking University（软件工程国家工程研究中心，北京大学）； Peking University Sixth Hospital（北京大学第六医院）； Augusta University（奥古斯塔大学）； Peking University First Hospital（北京大学第一医院）

Comments CVPR 2025

2502.20087 2025-10-13 cs.CV

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

Meng Lou, Yizhou Yu

机构 * School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）

Comments Accepted by CVPR 2025 (Oral)

2403.19979 2025-10-13 cs.CV cs.AI cs.LG

Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning

Qinhao Zhou, Yuwen Tan, Boqing Gong, Xiang Xiang

机构 * HUST AI & Visual Learning Lab (HAIV Lab)（华中科技大学人工智能与视觉学习实验室）； Huazhong University of Science and Technology (HUST)（华中科技大学）； Department of Computer Science（计算机科学系）； Boston University（波士顿大学）； ByteDance, Inc.（字节跳动公司）

Comments Journal extension of SSIAT (CVPR 2024)

1812.06145 2025-10-13 cs.CV cs.AI cs.HC cs.LG stat.ML

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training

Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel

Journal ref The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1165-1174

2003.08791 2025-10-10 cs.CV cs.LG eess.IV

High-Resolution Daytime Translation Without Domain Labels

Ivan Anokhin, Pavel Solovev, Denis Korzhenkov, Alexey Kharlamov, Taras Khakhulin, Alexey Silvestrov, Sergey Nikolenko, Victor Lempitsky, Gleb Sterkin

Comments accepted to CVPR 2020

2306.10354 2025-10-09 cs.CV cs.CL

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning

Yolo Yunlong Tang, Jinrui Zhang, Xiangchen Wang, Teng Wang, Feng Zheng

机构 * SUSTech VIP Lab（四川大学VIP实验室）

Comments Winner solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2023 workshop)

2510.04797 2025-10-07 cs.CV cs.AI

DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing

Qi Li, Shuwen Qiu, Julien Han, Xingzi Xu, Mehmet Saygin Seyfioglu, Kee Kiat Koo, Karim Bouyarmane

机构 * Amazon（亚马逊）； University of California, Los Angeles（加州大学洛杉矶分校）； Duke University（杜克大学）

Comments Submitted to CVPR 2025 and Published at CVPR 2025 AI for Content Creation workshop

2411.18625 2025-10-07 cs.CV cs.AI cs.GR eess.IV

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, Jia-Bin Huang, Johannes Kopf, Gordon Wetzstein, Changil Kim

Comments Will be presented at CVPR 2025. Project website: https://textured-gaussians.github.io/

2412.11100 2025-10-07 cs.CV

DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes

Jinxiu Liu, Shaoheng Lin, Yinxiao Li, Ming-Hsuan Yang

机构 * South China University of Technology（南方科技大学）； Google DeepMind（谷歌DeepMind）； UC Merced（加州大学默塞德分校）

Comments CVPR 2025

2211.10655 2025-10-06 cs.CV cs.AI cs.LG

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Hyungjin Chung, Dohoon Ryu, Michael T. McCann, Marc L. Klasky, Jong Chul Ye

Comments 14 pages, 10 figures

Journal ref 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 22542-22551

2509.26025 2025-10-01 cs.CV

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution

Shian Du, Menghan Xia, Chang Liu, Xintao Wang, Jing Wang, Pengfei Wan, Di Zhang, Xiangyang Ji

机构 * Tsinghua University（清华大学）； Kling Team, Kuaishou Technology（快手科技 Kling 团队）； Beijing Institute of Technology（北京理工大学）

Comments CVPR 2025

1904.05877 2025-10-01 cs.LG cs.CV stat.ML

Max-Sliced Wasserstein Distance and its use for GANs

Ishan Deshpande, Yuan-Ting Hu, Ruoyu Sun, Ayis Pyrros, Nasir Siddiqui, Sanmi Koyejo, Zhizhen Zhao, David Forsyth, Alexander Schwing

Comments Accepted to CVPR 2019

2503.14880 2025-09-30 cs.CV

DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar, Xiangyang Ji, Xu-Cheng Yin

机构 * University of Science and Technology Beijing（北京科技大学）； University of São Paulo（圣保罗大学）； Tsinghua University（清华大学）

Comments Accepted at CVPR 2025. The code and dataset are available at https://github.com/hmorimitsu/ptlflow/tree/main/ptlflow/models/dpflow. 24 pages, 17 figures

Journal ref 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025, pp. 17810-17820

2412.09622 2025-09-30 cs.CV

LoRACLR: Contrastive Adaptation for Customization of Diffusion Models

Enis Simsar, Thomas Hofmann, Federico Tombari, Pinar Yanardag

机构 * ETH Zürich（苏黎世联邦理工学院）； TU Munich（慕尼黑技术大学）； Google（谷歌）； Virginia Tech（弗吉尼亚理工大学）

Comments Accepted to CVPR'25. Project page: https://loraclr.github.io/

2412.21206 2025-09-30 cs.CV

PERSE: Personalized 3D Generative Avatars from A Single Portrait

Hyunsoo Cha, Inhee Lee, Hanbyul Joo

Comments Accepted to CVPR 2025, Project Page: https://hyunsoocha.github.io/perse/

2509.22412 2025-09-29 cs.CV

FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing

Hossein Kashiani, Niloufar Alipour Talemi, Fatemeh Afghah

机构 * Clemson University（克莱姆森大学）

Comments Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)

2502.02588 2025-09-29 cs.CV

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

Kyungmin Lee, Xiaohang Li, Qifei Wang, Junfeng He, Junjie Ke, Ming-Hsuan Yang, Irfan Essa, Jinwoo Shin, Feng Yang, Yinxiao Li

机构 * Google DeepMind（谷歌DeepMind）； KAIST（韩国科学技术院）； Google（谷歌）； Google Research（谷歌研究）； Georgia Institute of Technology（佐治亚理工学院）

Comments CVPR 2025, Project page: https://kyungmnlee.github.io/capo.github.io/

2509.21363 2025-09-29 cs.CV cs.AI

A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised

Runmin Wu, Mengyang Feng, Wenlong Guan, Dong Wang, Huchuan Lu, Errui Ding

机构 * Dalian University of Technology（大连理工大学）； Department of Computer Vision Technology (VIS), Baidu Inc.（计算机视觉技术部（VIS），百度公司）

Comments 11 pages

Journal ref CVPR.2019.00834

2509.20524 2025-09-26 cs.CV cs.AI

InstructVTON: Optimal Auto-Masking and Natural-Language-Guided Interactive Style Control for Inpainting-Based Virtual Try-On

Julien Han, Shuwen Qiu, Qi Li, Xingzi Xu, Mehmet Saygin Seyfioglu, Kavosh Asadi, Karim Bouyarmane

机构 * Amazon（亚马逊公司）； University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）； Duke University（杜克大学）

Comments Submitted to CVPR 2025 and Published at CVPR 2025 AI for Content Creation workshop

2501.08643 2025-09-26 cs.CV

MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors

Junda Cheng, Wenjing Liao, Zhipeng Cai, Longliang Liu, Gangwei Xu, Xianqi Wang, Yuzhou Wang, Zikang Yuan, Yong Deng, Jinliang Zang, Yangyang Shi, Jinhui Tang, Xin Yang

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology（电子信息与通讯学院，华中科技大学）； Meta ； AI Chip Center, Hong Kong University of Science and Technology（香港科技大学人工智能芯片中心）； Nanjing Forestry University（南京林业大学）； Autel Robotics

Comments MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors, is the extended journal version of our earlier conference paper (arXiv:2501.08643) accepted to CVPR 2025

2509.20343 2025-09-25 cs.CV

Efficient Encoder-Free Pose Conditioning and Pose Control for Virtual Try-On

Qi Li, Shuwen Qiu, Julien Han, Xingzi Xu, Mehmet Saygin Seyfioglu, Kee Kiat Koo, Karim Bouyarmane

机构 * Amazon（亚马逊）； University of California, Los Angeles（加州大学洛杉矶分校）； Duke University（杜克大学）

Comments Submitted to CVPR 2025 and Published at CVPR 2025 AI for Content Creation workshop

2506.02547 2025-09-25 cs.CV cs.ET

Probabilistic Online Event Downsampling

Andreu Girbau-Xalabarder, Jun Nagata, Shinichi Sumiyoshi, Ricard Marsal, Shin'ichi Satoh

机构 * Denso IT Laboratory（电通IT实验室）； National Institute of Informatics（信息处理研究所）

Comments Best paper award finalist at CVPR 2025 Event-Vision workshop

2412.07772 2025-09-25 cs.CV

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang

机构 * MIT（麻省理工学院）； Adobe（Adobe公司）

Comments CVPR 2025. Project Page: https://causvid.github.io/

2504.13499 2025-09-23 cs.CV

U-Shape Mamba: State Space Model for faster diffusion

Alex Ergasti, Filippo Botti, Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi, Andrea Prati

机构 * University of Parma（帕尔马大学）； University of Siena（锡耶纳大学）

Comments Accepted at CVPR 2025 eLVM workshop. The code is here: https://github.com/ErgastiAlex/U-Shape-Mamba

2504.10880 2025-09-23 cs.CV cs.RO

Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task

Aviral Chharia, Tianyu Ren, Tomotake Furuhata, Kenji Shimada

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

Comments CVPR Workshop 2025; Project Website: https://Safe-Construct.github.io/Safe-Construct

Journal ref CVPR, Nashville, TN, USA, 2025, pp. 5811-5820

2405.05587 2025-09-22 cs.CV cs.LG

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse

Yining Wang, Junjie Sun, Chenyue Wang, Mi Zhang, Min Yang

机构 * School of Computer Science, Fudan University, China（复旦大学计算机学院）

Comments CVPR 2024 Highlight

2509.13506 2025-09-18 cs.CV

DEFT-VTON: Efficient Virtual Try-On with Consistent Generalised H-Transform

Xingzi Xu, Qi Li, Shuwen Qiu, Julien Han, Karim Bouyarmane

机构 * Amazon（亚马逊公司）； Duke University（杜克大学）； University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）

Comments Published in 2025 CVPR Workshop

2408.07243 2025-09-18 cs.CV cs.IT math.IT

Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks

Raghavendra Singh

机构 * Ashoka University（阿什oka大学）

Comments NON ARCHIVAL PRESENTATION 1st workshop on Dataset Distillation CVPR 2024

2509.13116 2025-09-17 cs.CV

Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving

Ruibo Li, Hanyu Shi, Zhe Wang, Guosheng Lin

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）； SenseTime Research, Hong Kong, China（时光科技研究院，香港，中国）

Comments An extension of our CVPR 2023 paper, "Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving," accepted for publication in TPAMI