3D 视觉

Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds

Xianhui Meng, Yukang Huo, Li Zhang, Liu Liu, Haonan Jiang, Yan Zhong, Pingrui Zhang, Cewu Lu, Jun Liu

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

USV Obstacles Detection and Tracking in Marine Environments

Yara AlaaEldin, Enrico Simetti, Francesca Odone

机构 * DIBRIS - Department of Computer Science, Bioengineering, Robotics and System Engineering（DIBRIS-计算机科学、生物工程、机器人与系统工程系） ； University of Genova（热那亚大学） 纠错

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

BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models

Shangfeng Huang, Ruisheng Wang, Xin Wang

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

UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs

Zhe Liu, Jinghua Hou, Xiaoqing Ye, Jingdong Wang, Hengshuang Zhao, Xiang Bai

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology (HUST), Wuhan, China（华中科技大学电子信息与通信学院） ； School of Software Engineering, Huazhong University of Science and Technology (HUST), Wuhan, China（华中科技大学软件工程学院） ； Department of Computer Science, The University of Hong Kong, Hong Kong (HKU) SAR, China（香港大学计算机系） ； Baidu Inc., Beijing, China（百度公司） 纠错

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

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

Zhe Li, Xiang Bai, Jieyu Zhang, Zhuangzhe Wu, Che Xu, Ying Li, Chengkai Hou, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； University of Washington（华盛顿大学） 纠错

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

Comments Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset

Lassi Ruoppa, Tarmo Hietala, Verneri Seppänen, Josef Taher, Teemu Hakala, Xiaowei Yu, Antero Kukko, Harri Kaartinen, Juha Hyyppä

机构 * Finnish Geospatial Research Institute FGI（芬兰地理空间研究 institute） ； The National Land Survey of Finland（芬兰国家土地调查局） ； Department of Remote Sensing and Photogrammetry（遥感与摄影测量系） ； Department of Built Environment, School of Engineering, Aalto University（环境学院，工程学院，阿alto大学） 纠错

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

Comments 39 pages, 9 figures

Been There, Scanned That: Nostalgia-Driven LiDAR Compression for Self-Driving Cars

Ali Khalid, Jaiaid Mobin, Sumanth Rao Appala, Avinash Maurya, Stephany Berrio Perez, M. Mustafa Rafique, Fawad Ahmad

机构 * Rochester Institute of Technology（罗切斯特理工学院） ； Vellore Institute of Technology（维洛尔理工学院） ； The University of Sydney（悉尼大学） 纠错

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

Multi-Mapcher: Loop Closure Detection-Free Heterogeneous LiDAR Multi-Session SLAM Leveraging Outlier-Robust Registration for Autonomous Vehicles

Hyungtae Lim, Daebeom Kim, Hyun Myung

机构 * Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（信息与决策系统实验室，麻省理工学院） ； School of Electrical Engineering, KAIST（电气工程学院，韩国科学技术院） 纠错

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

Comments 13 pages, 12 figures

SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding

Qianqian Sun, Jixiang Luo, Dell Zhang, Xuelong Li

机构 * Institute of Artificial Intelligence(TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信） ； The University of Hongkong（香港大学） 纠错

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

A Practical-Driven Framework for Transitioning Drive-by-Wire to Autonomous Driving Systems: A Case Study with a Chrysler Pacifica Hybrid Vehicle

Dada Zhang, Md Ruman Islam, Pei-Chi Huang, Chun-Hsing Ho

机构 * Durham School of Architectural Engineering and Construction University of Nebraska-Lincoln（达勒姆建筑工程与建设学院 俄克拉荷马州立大学） ； Department of Computer Science University of Nebraska-Omaha（计算机科学系 俄克拉荷马州立大学） 纠错

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

Comments This updated version includes further implementation details and experimental validation. Accepted for presentation at The 22nd International Conference on Automation Technology (AUTOMATION 2025), Taipei, Taiwan, November 2025

3D Equivariant Visuomotor Policy Learning via Spherical Projection

Boce Hu, Dian Wang, David Klee, Heng Tian, Xupeng Zhu, Haojie Huang, Robert Platt, Robin Walters

机构 * Northeastern University（东北大学） ； Stanford University（斯坦福大学） 纠错

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

Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space

Weichen Zhang, Zile Zhou, Xin Zeng, Xuchen Liu, Jianjie Fang, Chen Gao, Yong Li, Jinqiang Cui, Xinlei Chen, Xiao-Ping Zhang

机构 * Tsinghua University（清华大学） ； Pengcheng Laboratory（鹏城实验室） ； Sun Yat-sen University（中山大学） 纠错

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

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

Ziwei Shi, Xiaoran Zhang, Wenjing Xu, Yan Xia, Yu Zang, Siqi Shen, Cheng Wang

机构 * Fujian Key Laboratory of Sensing and Computing for Smart Cities, Xiamen University, China（福建智能城市感知与计算重点实验室，厦门大学，中国） ； Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（多媒体可信感知与高效计算重点实验室，中华人民共和国教育部，厦门大学，中国） ； University of Science and Technology of China, China（中国科学技术大学，中国） 纠错

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

Comments 17 pages, 7 figures, NeurIPS 2025

Workspace Registration and Collision Detection for Industrial Robotics Applications

Klaus Zauner, Josef El Dib, Hubert Gattringer, Andreas Mueller

机构 * Institute of Robotics（机器人研究所） ； Johannes Kepler University（约翰·凯撒大学） 纠错

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

Journal ref Proceedings AIRoV - The First Austrian Symposium on AI, Robotics, and Vision, 25.-27.3.2024, Innsbruck, March 2024

Breaking the Static Assumption: A Dynamic-Aware LIO Framework Via Spatio-Temporal Normal Analysis

Chen Zhiqiang, Le Gentil Cedric, Lin Fuling, Lu Minghao, Qiao Qiyuan, Xu Bowen, Qi Yuhua, Lu Peng

机构 * Department of Mechanical Engineering, The University of Hong Kong（香港大学机械工程系） ； Autonomous Space Robotics Lab, University of Toronto Institute for Aerospace Studies (UTIAS)（多伦多大学航空航天研究学院自主空间机器人实验室） ； The School of Systems Science and Engineering, Sun Yatsen University（中山大学系统科学与工程学院） 纠错

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

Comments 8 pages, 7 figures, Accepted to IEEE Robotics and Automation Letters (RA-L)

Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark

Bingchen Miao, Wenqiao Zhang, Juncheng Li, Wangyu Wu, Siliang Tang, Zhaocheng Li, Haochen Shi, Jun Xiao, Yueting Zhuang

机构 * Zhejiang University（浙江大学） ； University of Liverpool（利物浦大学） 纠错

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

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective

Ziwei Zhang, Xin Wang, Zeyang Zhang, Peng Cui, Wenwu Zhu

机构 * Department of Computer Science and Technology（计算机科学与技术系） 纠错

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

Comments 13 pages; accepted by IEEE TPAMI

AutoScape: Geometry-Consistent Long-Horizon Scene Generation

Jiacheng Chen, Ziyu Jiang, Mingfu Liang, Bingbing Zhuang, Jong-Chyi Su, Sparsh Garg, Ying Wu, Manmohan Chandraker

机构 * NEC Labs America（NEC美国实验室） ； Simon Fraser University（西蒙弗雷泽大学） ； Northwestern University（西北大学） ； UC San Diego（加州大学圣地亚哥分校） 纠错

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

Comments ICCV 2025. Project page: https://auto-scape.github.io

Integrating BIM and UAV-based photogrammetry for Automated 3D Structure Model Segmentation

Siqi Chen, Shanyue Guan

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

IRIS: An Immersive Robot Interaction System

Xinkai Jiang, Qihao Yuan, Enes Ulas Dincer, Hongyi Zhou, Ge Li, Xueyin Li, Xiaogang Jia, Timo Schnizer, Nicolas Schreiber, Weiran Liao, Julius Haag, Kailai Li, Gerhard Neumann, Rudolf Lioutikov

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； University of Groningen（格罗宁根大学） 纠错

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

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR

Adwait Chandorkar, Hasan Tercan, Tobias Meisen

机构 * Institute for TMDT, University of Wuppertal, Germany（TMDT研究所，乌尔姆大学） 纠错

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

Comments Best Paper Award at the Embedded Vision Workshop ICCV 2025

Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Method

Shengjing Tian, Xiantong Zhao, Yuhao Bian, Yinan Han, Bin Liu

机构 * School of Economics and Management, China University of Mining and Technology（经济管理学院，中国矿业大学） 纠错

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

GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization

Dušan Malić, Christian Fruhwirth-Reisinger, Alexander Prutsch, Wei Lin, Samuel Schulter, Horst Possegger

机构 * Institute of Visual Computing, Graz University of Technology（视觉计算研究所，格拉茨技术大学） ； Christian Doppler Laboratory for Embedded Machine Learning（嵌入式机器学习克里斯蒂安多普勒实验室） ； Institute for Machine Learning, Johannes Kepler University Linz（机器学习研究所，约翰·凯撒大学林茨） ； Amazon（亚马逊） 纠错

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

Comments 1st place at the IROS'25 RoboSense Challenge, Track #3: Cross-Sensor Placement 3D Object Detection

BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining

Ajinkya Khoche, Gergő László Nagy, Maciej Wozniak, Thomas Gustafsson, Patric Jensfelt

机构 * KTH Royal Institute of Technology（皇家理工学院） ； Scania CV AB（斯堪尼亚公司） 纠错

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

Comments Under Review

Moving Object Detection from Moving Camera Using Focus of Expansion Likelihood and Segmentation

Masahiro Ogawa, Qi An, Atsushi Yamashita

机构 * Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo（精密工程学系，工学研究生院，东京大学） ； Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo（人类与工程环境研究系，前沿科学研究生院，东京大学） 纠错

专题命中 点云 ：3D reconstruction(abstract)；分类 cs.CV

Comments 8 pages, 15 figures, RA-L submission

Towards 3D Objectness Learning in an Open World

Taichi Liu, Zhenyu Wang, Ruofeng Liu, Guang Wang, Desheng Zhang

机构 * Rutgers University（罗格斯大学） ； Tsinghua University（清华大学） ； Michigan State University（密歇根州立大学） ； Florida State University（佛罗里达州立大学） 纠错

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

Comments Accepted by NeurIPS 2025

Pole-Image: A Self-Supervised Pole-Anchored Descriptor for Long-Term LiDAR Localization and Map Maintenance

Wuhao Xie, Kanji Tanaka

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

Comments 4 pages, technical report

ERNet: Efficient Non-Rigid Registration Network for Point Sequences

Guangzhao He, Yuxi Xiao, Zhen Xu, Xiaowei Zhou, Sida Peng

机构 * Zhejiang University（浙江大学） 纠错

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

Comments Accepted to ICCV 2025. Project Page: https://guangzhaohe.com/ernet

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, Haoang Li

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Tsinghua University（清华大学） ； Westlake University（西湖大学） ； Zhejiang University（浙江大学） ； South China University of Technology（华南理工大学） 纠错

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

UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection

Xin Jin, Haisheng Su, Kai Liu, Cong Ma, Wei Wu, Fei Hui, Junchi Yan

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Chang’an University（长安大学） ； SenseAuto Research（SenseAuto研究院） ； Tsinghua University（清华大学） 纠错

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

Comments Accepted to CVPR2025