3D 视觉 - arXivDaily 专题

2503.18254 2025-10-14 cs.CV cs.GR 62%

Surface-Aware Distilled 3D Semantic Features

Lukas Uzolas, Elmar Eisemann, Petr Kellnhofer

机构 * Delft University of Technology（代尔夫特理工大学）

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV、cs.GR

2510.11687 2025-10-14 cs.CV 57%

Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View

Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu

机构 * Fudan University（复旦大学）； Shanghai Innovation Institute（上海创新研究院）

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2510.11632 2025-10-14 cs.CV cs.AI cs.LG 57%

NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection

Krittin Chaowakarn, Paramin Sangwongngam, Nang Htet Htet Aung, Chalie Charoenlarpnopparut

机构 * The School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University（信息、计算机与通信技术学院，Sirindhorn国际技术学院，泰国朱拉隆梭大学）； National Electronics and Computer Technology Center, National Science and Technology Development Agency（国家电子与计算机技术中心，国家科学技术发展局）； Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University（电气工程系，工程学院，朱拉隆梭大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2510.07723 2025-10-14 cs.CV 57%

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Wenyue Chen, Peng Li, Wangguandong Zheng, Chengfeng Zhao, Mengfei Li, Yaolong Zhu, Zhiyang Dou, Ronggang Wang, Yuan Liu

机构 * PKU（北京大学）； HKUST（香港科技大学）； SEU（上海师范大学）； HKU（香港大学）

专题命中三维重建：3D generation(abstract)；分类 cs.CV

Comments NeurIPS 2025 https://xishuxishu.github.io/SyncHuman.github.io/

2510.10406 2025-10-14 cs.CV cs.AI cs.LG 57%

Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes

Zhao-Yang Wang, Jieneng Chen, Jiang Liu, Yuxiang Guo, Rama Chellappa

机构 * Johns Hopkins University（约翰霍普金斯大学）； Advanced Micro Devices, Inc.（先进微器件公司）

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2412.01770 2025-10-14 cs.RO cs.AI cs.LG 57%

Robot Learning with Super-Linear Scaling

Marcel Torne, Arhan Jain, Jiayi Yuan, Vidaaranya Macha, Lars Ankile, Anthony Simeonov, Pulkit Agrawal, Abhishek Gupta

机构 * Massachusets Institute of Technology（麻省理工学院）； University of Washington（华盛顿大学）； Stanford University（斯坦福大学）

专题命中三维重建：3D reconstruction(abstract)；分类 cs.RO

2404.11195 2025-10-14 cond-mat.mtrl-sci cond-mat.mes-hall physics.comp-ph 50%

Texture tomography, a versatile framework to study crystalline texture in 3D

M. P. K. Frewein, J. K. Mason, B. Maier, H. Cölfen, M. Burghammer, A. A. Medjahed, M. Allain, T. A. Grünewald

专题命中三维重建：3D reconstruction(abstract)

1. 三维重建 7 篇