CVPR

Structure from Collision

Takuhiro Kaneko

机构 * NTT Corporation（日本通信用电讯公司） 纠错

Comments Accepted to CVPR 2025 (Highlight). Project page: https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/sfc/

PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter

Yaohua Zha, Yanzi Wang, Hang Guo, Jinpeng Wang, Tao Dai, Bin Chen, Zhihao Ouyang, Xue Yuerong, Ke Chen, Shu-Tao Xia

机构 * Tsinghua University（清华大学） ； Pengcheng Laboratory（鹏城实验室） ； Shenzhen University（深圳大学） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Meta 纠错

Comments Accepted to CVPR 2025

HuMoCon: Concept Discovery for Human Motion Understanding

Qihang Fang, Chengcheng Tang, Bugra Tekin, Shugao Ma, Yanchao Yang

机构 * The University of Hong Kong（香港大学） ； Meta 纠错

Comments 18 pages, 10 figures

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)

Exploring Timeline Control for Facial Motion Generation

Yifeng Ma, Jinwei Qi, Chaonan Ji, Peng Zhang, Bang Zhang, Zhidong Deng, Liefeng Bo

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Tongyi Lab, Alibaba Group（阿里云实验室） 纠错

Comments Accepted by CVPR 2025, Project Page: https://humanaigc.github.io/facial-motion-timeline-control/

ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval

Eric Xing, Pranavi Kolouju, Robert Pless, Abby Stylianou, Nathan Jacobs

机构 * Washington University in St. Louis（华盛顿大学圣路易斯分校） ； Saint Louis University（圣路易斯大学） ； The George Washington University（乔治华盛顿大学） 纠错

Comments 15 pages, 8 figures, 6 tables. CVPR 2025

HCQA-1.5 @ Ego4D EgoSchema Challenge 2025

Haoyu Zhang, Yisen Feng, 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 third-place solution for the Ego4D EgoSchema Challenge at the CVPR EgoVis Workshop 2025

PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation

HsiaoYuan Hsu, Yuxin Peng

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学计算机科学技术研究院） 纠错

Comments Accepted to CVPR 2025. Minor editing issue fixed. Code and dataset are available at https://thekinsley.github.io/PosterO/

Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation

Peihua Deng, Jiehua Zhang, Xichun Sheng, Chenggang Yan, Yaoqi Sun, Ying Fu, Liang Li

Comments Accepted by CVPR 2025

PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment

Tianchen Deng, Guole Shen, Tong Qin, Jianyu Wang, Wentao Zhao, Jingchuan Wang, Danwei Wang, Weidong Chen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted by CVPR 2024

MotionPro: A Precise Motion Controller for Image-to-Video Generation

Zhongwei Zhang, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Wu Liu, Ting Yao, Tao Mei

机构 * University of Science and Technology of China（中国科学技术大学） ； HiDream.ai Inc.（HiDream.ai公司） 纠错

Comments CVPR 2025. Project page: https://zhw-zhang.github.io/MotionPro-page/

Category-Agnostic Neural Object Rigging

Guangzhao He, Chen Geng, Shangzhe Wu, Jiajun Wu

机构 * Stanford University（斯坦福大学） ； University of Cambridge（剑桥大学） 纠错

Comments Accepted to CVPR 2025. Project Page: https://guangzhaohe.com/canor

Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks

Chang Liu, Haomin Zhang, Shiyu Xia, Zihao Chen, Chaofan Ding, Xin Yue, Huizhe Chen, Xinhan Di

机构 * AI Lab, Giant Network（AI实验室，巨人网络） ； University of Trento（特伦托大学） 纠错

Comments 4 pages, 1 figure, accepted by CVPR 2025 MMFM Workshop

Can Visual Encoder Learn to See Arrows?

Naoyuki Terashita, Yusuke Tozaki, Hideaki Omote, Congkha Nguyen, Ryosuke Nakamoto, Yuta Koreeda, Hiroaki Ozaki

机构 * Hitachi, Ltd.（日本日立株式会社） ； Kyoto Sangyo University（京都 Sangyo 大学） ； Gifu University（岐阜大学） 纠错

Comments This work has been accepted for poster presentation at the Second Workshop on Visual Concepts in CVPR 2025

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

Ziqiao Peng, Yanbo Fan, Haoyu Wu, Xuan Wang, Hongyan Liu, Jun He, Zhaoxin Fan

机构 * Renmin University of China（中国人民大学） ； Ant Group（蚂蚁集团） ； Tsinghua University（清华大学） ； Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算创新中心） 纠错

Comments Accepted by CVPR 2025

Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?

Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； NVIDIA（英伟达） ； University of Ottawa（渥太华大学） 纠错

Comments Accepted at CVPR 2025. 22 pages, 16 figures

GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis

You Wang, Li Fang, Hao Zhu, Fei Hu, Long Ye, Zhan Ma

Comments CVPR 2025

Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction

Li Fang, Hao Zhu, Longlong Chen, Fei Hu, Long Ye, Zhan Ma

Comments CVPR 2025

Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition

Wen Yin, Yong Wang, Guiduo Duan, Dongyang Zhang, Xin Hu, Yuan-Fang Li, Tao He

机构 * The Laboratory of Intelligent Collaborative Computing of UESTC（UESTC智能协同计算实验室） ； Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province（四川省 ubiquitous intelligence and trusted services 重点实验室） ； Faculty of Information Technology, Monash University（墨尔本大学信息技术学院） 纠错

Comments Accepted at CVPR 2025

Rotation-Equivariant Self-Supervised Method in Image Denoising

Hanze Liu, Jiahong Fu, Qi Xie, Deyu Meng

机构 * Xi’an Jiaotong University（西安交通大学） ； Pengcheng Laboratory（鹏城实验室） ； Macau University of Science and Technology（澳门科学技术大学） 纠错

Comments Accepted by CVPR 2025

Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency

Hyunho Ha, Lei Xiao, Christian Richardt, Thu Nguyen-Phuoc, Changil Kim, Min H. Kim, Douglas Lanman, Numair Khan

Comments Accepted by CVPR 2025. Project website: https://nkhan2.github.io/projects/geometry-guided-2025/index.html

Digital Overconsumption and Waste: A Closer Look at the Impacts of Generative AI

Vanessa Utz, Steve DiPaola

Comments Conference on Computer Vision and Pattern Recognition (CVPR) 2023. Ethical Considerations in Creative Applications of Computer Vision (EC3V) Workshop

Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding

Tianyu Chen, Xingcheng Fu, Yisen Gao, Haodong Qian, Yuecen Wei, Kun Yan, Haoyi Zhou, Jianxin Li

机构 * SKLCCSE, School of Computer Science and Engineering, Beihang University, China（信息与通信工程学院，北京航空航天大学） ； School of Software, Beihang University, China（软件学院，北京航空航天大学） ； Key Lab of Education Blockchain and Intelligent Technology, Guangxi Normal University, China（教育区块链与智能技术重点实验室，广西师范大学） ； Institute of Artificial Intelligence, Beihang University, Beijing, China（人工智能研究院，北京航空航天大学） 纠错

Comments CVPR(Highlight)

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

Hongjie Wang, Chih-Yao Ma, Yen-Cheng Liu, Ji Hou, Tao Xu, Jialiang Wang, Felix Juefei-Xu, Yaqiao Luo, Peizhao Zhang, Tingbo Hou, Peter Vajda, Niraj K. Jha, Xiaoliang Dai

机构 * Princeton University（普林斯顿大学） ； Meta 纠错

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

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliege, Anthony Cioppa, Silvio Giancola, Andrea Vedaldi, Bernard Ghanem, Marc Van Droogenbroeck

机构 * University of Liège（利根大学） ； KAUST（科威特高级科学研究中心） ； University of Oxford（牛津大学） 纠错

Comments Accepted at CVPR 2025 as Highlight. 13 pages, 13 figures, 10 tables

Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification

Puru Vaish, Shunxin Wang, Nicola Strisciuglio

Comments Accepted at CVPR 2024

Syn3DTxt: Embedding 3D Cues for Scene Text Generation

Li-Syun Hsiung, Jun-Kai Tu, Kuan-Wu Chu, Yu-Hsuan Chiu, Yan-Tsung Peng, Sheng-Luen Chung, Gee-Sern Jison Hsu

机构 * National Taiwan University of Science and Technology（台湾科技大学） ； National Chengchi University（中正大学） 纠错

Comments CVPR workshop 2025: SyntaGen

PromptHMR: Promptable Human Mesh Recovery

Yufu Wang, Yu Sun, Priyanka Patel, Kostas Daniilidis, Michael J. Black, Muhammed Kocabas

Comments CVPR 2025. Project website: https://yufu-wang.github.io/phmr-page

PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

Uyoung Jeong, Jonathan Freer, Seungryul Baek, Hyung Jin Chang, Kwang In Kim

机构 * UNIST（全南大学） ； University of Birmingham（伯明翰大学） ； POSTECH 纠错

Comments accepted to CVPR 2025

Selective Structured State Space for Multispectral-fused Small Target Detection

Qianqian Zhang, WeiJun Wang, Yunxing Liu, Li Zhou, Hao Zhao, Junshe An, Zihan Wang

机构 * Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学） ； National Space Science Center, Chinese Academy of Sciences（中国科学院国家空间科学中心） ； School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院） ； School of Astronomy and Space Science, University of Chinese Academy of Sciences（中国科学院大学天文与空间科学学院） ； School of Computing, National University of Singapore（新加坡国立大学计算机学院） 纠错

Comments This work was submitted to CVPR 2025, but was rejected after being reviewed by 7 reviewers. After revision, it is currently under review

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining

Yunze Liu, Li Yi

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025