CVPR

Hearing Anywhere in Any Environment

Xiulong Liu, Anurag Kumar, Paul Calamia, Sebastia V. Amengual, Calvin Murdock, Ishwarya Ananthabhotla, Philip Robinson, Eli Shlizerman, Vamsi Krishna Ithapu, Ruohan Gao

机构 * University of Washington（华盛顿大学） ； Meta ； University of Maryland, College Park（马里兰大学帕克分校） 纠错

Comments CVPR 2025; Project Page: https://dragonliu1995.github.io/hearinganywhereinanyenvironment/

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

Hengyu Liu, Yuehao Wang, Chenxin Li, Ruisi Cai, Kevin Wang, Wuyang Li, Pavlo Molchanov, Peihao Wang, Zhangyang Wang

机构 * The Chinese University of Hong Kong（香港中文大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Nvidia（英伟达） 纠错

Comments CVPR 2025; Project Page: https://flexgs.github.io

Vocabulary-free few-shot learning for Vision-Language Models

Maxime Zanella, Clément Fuchs, Ismail Ben Ayed, Christophe De Vleeschouwer

机构 * UCLouvain（乌得勒支大学） ； UMons（蒙斯大学） ； ÉTS Montreal（蒙特利尔ÉTS） 纠错

Comments Accepted at CVPR Workshops 2025

Learning from Noise: Enhancing DNNs for Event-Based Vision through Controlled Noise Injection

Marcin Kowalczyk, Kamil Jeziorek, Tomasz Kryjak

Journal ref IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Nashville, 2025

OSGNet @ Ego4D Episodic Memory Challenge 2025

Yisen Feng, Haoyu Zhang, Qiaohui Chu, Meng Liu, Weili Guan, Yaowei Wang, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Pengcheng Laboratory（鹏城实验室） ； Shandong Jianzhu University（山东建筑大学） 纠错

Comments The champion solutions for the three egocentric video localization tracks(Natural Language Queries, Goal Step, and Moment Queries tracks) of the Ego4D Episodic Memory Challenge at CVPR EgoVis Workshop 2025

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives

Aniruddh Sikdar, Aditya Gandhamal, Suresh Sundaram

机构 * Robert Bosch Centre for Cyber Physical Systems, Indian Institute of Science, Bengaluru, India（罗伯特·博世协同物理系统中心，印度科学研究院，班加罗尔） ； Kotak IISc AI-ML Centre, Indian Institute of Science, Bengaluru, India（Kotak IISc AI-ML 中心，印度科学研究院，班加罗尔） ； Department of Aerospace Engineering, Indian Institute of Science, Bengaluru, India（航空航天工程系，印度科学研究院，班加罗尔） 纠错

Comments Accepted at Workshop on Foundation Models Meet Embodied Agents at CVPR 2025 (Non-archival Track)

OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentation

Aditya Gandhamal, Aniruddh Sikdar, Suresh Sundaram

机构 * Kotak IISc AI-ML Centre, Indian Institute of Science, Bengaluru, India（Kotak IISc AI-ML 中心，印度科学学院，班加罗尔，印度） ； Robert Bosch Centre for Cyber Physical Systems, Indian Institute of Science, Bengaluru, India（罗伯特·博世网络物理系统中心，印度科学学院，班加罗尔，印度） ； Department of Aerospace Engineering, Indian Institute of Science, Bengaluru, India（航空工程系，印度科学学院，班加罗尔，印度） 纠错

Comments Accepted at CVPR 2025 Workshop on Transformers for Vision (Non-archival track)

Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori

机构 * Kyoto University（京都大学） ； National Institute of Informatics（国家信息研究所） ； Sony Interactive Entertainment（索尼互动娱乐） 纠错

Comments CVPR 2025

SemNav: A Model-Based Planner for Zero-Shot Object Goal Navigation Using Vision-Foundation Models

Arnab Debnath, Gregory J. Stein, Jana Kosecka

机构 * George Mason University（乔治·马歇尔大学） 纠错

Comments Accepted at CVPR 2025 workshop - Foundation Models Meet Embodied Agents

Heterogeneous Skeleton-Based Action Representation Learning

Hongsong Wang, Xiaoyan Ma, Jidong Kuang, Jie Gui

机构 * School of Computer Science and Engineering, Southeast University, Nanjing 210096, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及交叉应用关键实验室（东南大学）） ； School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China（东南大学网络科学与工程学院） ； Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education, China（区块链应用、监督与管理工程研究中心（东南大学）） ； Purple Mountain Laboratories, Nanjing 210000, China（紫金山实验室） 纠错

Comments To appear in CVPR 2025

Hybrid Ensemble of Segmentation-Assisted Classification and GBDT for Skin Cancer Detection with Engineered Metadata and Synthetic Lesions from ISIC 2024 Non-Dermoscopic 3D-TBP Images

Muhammad Zubair Hasan, Fahmida Yasmin Rifat

机构 * University of North Texas（北卡罗来纳州立大学） 纠错

Comments Written as per the requirements of CVPR 2025. It is a 8 page paper without reference

SportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team Sports

Dheeraj Khanna, Jerrin Bright, Yuhao Chen, John S. Zelek

机构 * University of Waterloo（滑铁卢大学） 纠错

Comments Paper accepted at CVSports IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW'25). The paper has 8 pages, including 6 Figures and 5 Tables

NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution

Marcos V. Conde, Radu Timofte, Zihao Lu, Xiangyu Kong, Xiaoxia Xing, Fan Wang, Suejin Han, MinKyu Park, Tianyu Zhang, Xin Luo, Yeda Chen, Dong Liu, Li Pang, Yuhang Yang, Hongzhong Wang, Xiangyong Cao, Ruixuan Jiang, Senyan Xu, Siyuan Jiang, Xueyang Fu, Zheng-Jun Zha, Tianyu Hao, Yuhong He, Ruoqi Li, Yueqi Yang, Xiang Yu, Guanlan Hong, Minmin Yi, Yuanjia Chen, Liwen Zhang, Zijie Jin, Cheng Li, Lian Liu, Wei Song, Heng Sun, Yubo Wang, Jinghua Wang, Jiajie Lu, Watchara Ruangsan

Comments CVPR 2025 - New Trends in Image Restoration and Enhancement (NTIRE)

MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps

Valentin Gabeff, Haozhe Qi, Brendan Flaherty, Gencer Sumbül, Alexander Mathis, Devis Tuia

机构 * EPFL（苏黎世联邦理工学院） 纠错

Comments CVPR 2025; Benchmark and code at: https://github.com/eceo-epfl/MammAlps. After submission of v1, we noticed that a few audio files were not correctly aligned with the corresponding video. We fixed the issue, which had little to no impact on performance. We also now report results for three runs

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

Souhail Hadgi, Luca Moschella, Andrea Santilli, Diego Gomez, Qixing Huang, Emanuele Rodolà, Simone Melzi, Maks Ovsjanikov

机构 * École polytechnique（巴黎政治学院） ； Sapienza University of Rome（罗马大学） ； University of Milano-Bicocca（米兰-布雷拉大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments CVPR 2025

EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space

Jianrong Zhang, Hehe Fan, Yi Yang

机构 * ReLER, AAII, University of Technology Sydney（技术悉尼大学） ； CCAI, Zhejiang University（浙江大学） 纠错

Comments Accepted to CVPR 2025. Project page: https://jiro-zhang.github.io/EnergyMoGen/

CondiMen: Conditional Multi-Person Mesh Recovery

Brégier Romain, Baradel Fabien, Lucas Thomas, Galaaoui Salma, Armando Matthieu, Weinzaepfel Philippe, Rogez Grégory

机构 * NAVER LABS Europe（NAVER LABS欧洲分公司） ； LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS（LIGM，巴黎综合理工学院，根西-埃菲尔大学，国家科学研究中心） 纠错

Comments accepted to the RHOBIN workshop at CVPR 2025

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders

Fiona Ryan, Ajay Bati, Sangmin Lee, Daniel Bolya, Judy Hoffman, James M. Rehg

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Sungkyunkwan University（全南大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments CVPR 2025 Highlight

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

Tal Zeevi, Ravid Shwartz-Ziv, Yann LeCun, Lawrence H. Staib, John A. Onofrey

机构 * Yale University（耶鲁大学） ； New York University（纽约大学） ； Meta FAIR 纠错

Comments Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025. Code available at: https://github.com/code-supplement-25/rate-in

Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator

Chaehun Shin, Jooyoung Choi, Heeseung Kim, Sungroh Yoon

机构 * Data Science and AI Laboratory, ECE, Seoul National University（数据科学与人工智能实验室、电子与计算机工程系、首尔国立大学） ； AIIS, ASRI, INMC, ISRC, and Interdisciplinary Program in AI, Seoul National University（人工智能研究所、人工智能研究室、智能网络与计算中心、信息科学与工程系以及人工智能交叉学科项目、首尔国立大学） 纠错

Comments CVPR 2025

Self-Supervised Spatial Correspondence Across Modalities

Ayush Shrivastava, Andrew Owens

机构 * University of Michigan（密歇根大学） 纠错

Comments CVPR 2025. Project link: https://www.ayshrv.com/cmrw . Code: https://github.com/ayshrv/cmrw

Dense Match Summarization for Faster Two-view Estimation

Jonathan Astermark, Anders Heyden, Viktor Larsson

机构 * Centre for Mathematical Sciences, Lund University（数学科学中心，隆德大学） 纠错

Comments Accepted to Computer Vision and Pattern Recognition (CVPR) 2025

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

Tongyuan Bai, Wangyuanfan Bai, Dong Chen, Tieru Wu, Manyi Li, Rui Ma

机构 * School of Artificial Intelligence, Jilin University（吉林大学人工智能学院） ； School of Software, Shandong University（山东大学软件学院） ； Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国） 纠错

Comments Accepted to CVPR 2025

Towards In-the-wild 3D Plane Reconstruction from a Single Image

Jiachen Liu, Rui Yu, Sili Chen, Sharon X. Huang, Hengkai Guo

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； University of Louisville（路易斯维尔大学） ； Bytedance（字节跳动） 纠错

Comments CVPR 2025 Highlighted Paper

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

Kunyu Wang, Xueyang Fu, Xin Lu, Chengjie Ge, Chengzhi Cao, Wei Zhai, Zheng-Jun Zha

机构 * School of Information Science and Technology and MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（信息科学与技术学院和脑启发智能感知与认知MoE重点实验室，中国科学技术大学） 纠错

Comments Accepted as CVPR 2025 oral paper

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

Johannes Schusterbauer, Ming Gui, Frank Fundel, Björn Ommer

Comments Accepted by CVPR 2025

MTevent: A Multi-Task Event Camera Dataset for 6D Pose Estimation and Moving Object Detection

Shrutarv Awasthi, Anas Gouda, Sven Franke, Jérôme Rutinowski, Frank Hoffmann, Moritz Roidl

机构 * TU Dortmund（图卢兹大学多特蒙德分校） ； Lamarr Institute for Machine Learning and Artificial Intelligence（拉玛尔机器学习与人工智能研究所） 纠错

Comments Accepted at 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Fifth International Workshop on Event-Based Vision

Journal ref IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025

S3D: Sketch-Driven 3D Model Generation

Hail Song, Wonsik Shin, Naeun Lee, Soomin Chung, Nojun Kwak, Woontack Woo

机构 * KAIST（韩国科学技术院） ； Seoul National University（首尔国立大学） 纠错

Comments Accepted as a short paper to the GMCV Workshop at CVPR'25

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video

Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards

机构 * Mila Quebec（蒙特利尔大学） ； McGill University（麦吉尔大学） ； Meta ； Université de Montréal（蒙特利尔大学） ； Imperial College London（伦敦帝国理工学院） ； Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫 Heinrich Hertz 研究所） ； Technological University Dublin（都柏林技术大学） ； Apollo Research（Apollo 研究所） 纠错

Comments 4 pages, 3 figures, 9 tables. Oral and Tutorial at the CVPR Mechanistic Interpretability for Vision (MIV) Workshop

Learning on Model Weights using Tree Experts

Eliahu Horwitz, Bar Cavia, Jonathan Kahana, Yedid Hoshen

机构 * The Hebrew University of Jerusalem（希伯来大学） 纠错

Comments CVPR 2025. Project page: https://horwitz.ai/probex/