3D 视觉 - arXivDaily 专题

2507.01439 2025-07-31 cs.CV 79%

TurboReg: TurboClique for Robust and Efficient Point Cloud Registration

Shaocheng Yan, Pengcheng Shi, Zhenjun Zhao, Kaixin Wang, Kuang Cao, Ji Wu, Jiayuan Li

机构 * School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感与信息工程学院）； Department of Computer and Systems Engineering, University of Zaragoza（阿拉维扎大学计算机与系统工程系）； College of Computer Science, Beijing University of Technology（北京理工大学计算机学院）； School of Computer Science, Wuhan University（武汉大学计算机学院）

专题命中点云：point cloud(title,abstract)；分类 cs.CV

Comments ICCV-2025 Accepted Paper

2506.21541 2025-07-31 cs.CV 79%

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning

Chuxin Wang, Yixin Zha, Wenfei Yang, Tianzhu Zhang

机构 * University of Science and Technology of China（中国科学技术大学）

专题命中点云：point cloud(title,abstract)；分类 cs.CV

Comments Accepted by ICCV 2025, website: https://chuxwa.github.io/project_StruMamba3D/

2507.22454 2025-07-31 cs.CV eess.IV 74%

TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation

Jiuming Liu, Zheng Huang, Mengmeng Liu, Tianchen Deng, Francesco Nex, Hao Cheng, Hesheng Wang

机构 * School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240（上海交通大学自动化与智能感知学院）； Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240（中国教育部系统控制与信息处理重点实验室）； University of Twente, Netherlands（荷兰埃因霍温理工大学）

专题命中点云：point cloud(title)；分类 cs.CV

Comments Accepted by IROS 2025. Code:https://github.com/IRMVLab/TopoLiDM

2507.22668 2025-07-31 cs.CV 70%

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation

Hongbin Lin, Yifan Jiang, Juangui Xu, Jesse Jiaxi Xu, Yi Lu, Zhengyu Hu, Ying-Cong Chen, Hao Wang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； University of Toronto（多伦多大学）

专题命中点云：point cloud(abstract)；spatial understanding(abstract)；分类 cs.CV

Comments 15 pages, 11 figures, to be published in ACMMM 2025 Conference

2507.22522 2025-07-31 cs.CV cs.AI cs.RO 62%

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

Ziyi Wang, Peiming Li, Hong Liu, Zhichao Deng, Can Wang, Jun Liu, Junsong Yuan, Mengyuan Liu

机构 * State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School（1 人工智能通用基础理论国家重点实验室，北京大学深圳研究生院）； Sun Yat-sen University（2 中山大学）； Kiel University（3 科尔堡大学）； Lancaster University（4 拉斯特纳大学）； State University of New York at Buffalo（5 纽约州立大学布法罗分校）

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 4 figures, Accepted to ICCV2025

2505.10696 2025-07-31 cs.RO cs.CV 62%

TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation

Manthan Patel, Fan Yang, Yuheng Qiu, Cesar Cadena, Sebastian Scherer, Marco Hutter, Wenshan Wang

机构 * Robotic Systems Lab, ETH Zurich（苏黎世联邦理工学院机器人系统实验室）； Robotics Institute of Carnegie Mellon University（卡内基梅隆大学机器人研究所）