3D 视觉

BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields

Rushil Desai

机构 * Berkeley Artificial Intelligence Research（伯克利人工智能研究） 纠错

专题命中 三维重建 ：NeRF(abstract)；Gaussian Splatting(abstract)；分类 cs.CV

Comments ICCV 2025 Workshops (11 Pages, 6 Figures, 2 Tables)

Online 3D Gaussian Splatting Modeling with Novel View Selection

Byeonggwon Lee, Junkyu Park, Khang Truong Giang, Soohwan Song

机构 * Department of Computer Science and Artificial Intelligence, Dongguk University（计算机科学与人工智能系，东国大学） ； dot, Seongnam-si, Gyeonggi-do（42dot，青nam市，京畿道） 纠错

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；3DGS(abstract)；分类 cs.CV

ActiveGAMER: Active GAussian Mapping through Efficient Rendering

Liyan Chen, Huangying Zhan, Kevin Chen, Xiangyu Xu, Qingan Yan, Changjiang Cai, Yi Xu

机构 * OPPO US Research Center（OPPO美国研究中心） ； Stevens Institute of Technology（史蒂文斯理工学院） 纠错

专题命中 Gaussian Splatting ：NeRF(abstract)；Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV、cs.RO

Comments Accepted to CVPR2025. Project page: https://oppo-us-research.github.io/ActiveGAMER-website/. Code: https://github.com/oppo-us-research/ActiveGAMER

Toward Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization

Mengjiao Han, Andres Sewell, Joseph Insley, Janet Knowles, Victor A. Mateevitsi, Michael E. Papka, Steve Petruzza, Silvio Rizzi

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)

Journal ref IEEE eScience 2025 Poster

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

Wen Jiang, Boshu Lei, Katrina Ashton, Kostas Daniilidis

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Archimedes, Athena RC（阿基米德、阿提卡RC） 纠错

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV、cs.RO

Comments ICCV 2025

Gaussian Primitives for Deformable Image Registration

Jihe Li, Xiang Liu, Fabian Zhang, Xia Li, Xixin Cao, Ye Zhang, Joachim Buhmann

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；分类 cs.CV

Journal ref Physics and Imaging in Radiation Oncology, p.100821 (2025)

Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet

Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari

机构 * Sirjan University of Technology（锡尔贾恩技术大学） ； Clemson University（克莱姆森大学） 纠错

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

Comments This paper has been accepted for presentation at the 7th International Conference on Pattern Recognition and Image Analysis (IPRIA 2025)

Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement

Kallol Saha, Amber Li, Angela Rodriguez-Izquierdo, Lifan Yu, Ben Eisner, Maxim Likhachev, David Held

机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） ； Princeton University（普林斯顿大学） 纠错

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

Comments Conference on Robot Learning (CoRL) 2025 (https://planning-from-point-clouds.github.io/)

LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds

Zhenrong Zhang, Jianan Liu, Yuxuan Xia, Tao Huang, Qing-Long Han, Hongbin Liu

机构 * School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University（人工智能与先进计算学院，西安交通大学利物浦大学） ； Momoni AI ； Department of Automation, Shanghai Jiaotong University（自动化学院，上海交通大学） ； College of Science and Engineering, James Cook University（科学与工程学院，詹姆斯库克大学） ； School of Engineering, Swinburne University of Technology（工程学院，斯威灵斯大学） 纠错

专题命中 点云 ：point cloud(title)；分类 cs.CV

Comments Accept by IEEE Transactions on Circuits and Systems for Video Technology

Domain Adaptation for Different Sensor Configurations in 3D Object Detection

Satoshi Tanaka, Kok Seang Tan, Isamu Yamashita

机构 * TIER IV, Inc（Tier IV公司） 纠错

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

Empowering Bridge Digital Twins by Bridging the Data Gap with a Unified Synthesis Framework

Wang Wang, Mingyu Shi, Jun Jiang, Wenqian Ma, Chong Liu, Yasutaka Narazaki, Xuguang Wang

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

Comments Due to the authors' failure to reach an agreement on the manuscript quality, they voluntarily waive their rights to be credited as authors