arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

共收录 19082 信号源:cs.CV, cs.GR, cs.RO

1. 点云 7740 篇

2602.05557 2026-02-06 cs.CV cs.RO 81%

PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds

PIRATR:基于变换器的参数化物体推理用于机器人应用的3D点云

Michael Schwingshackl, Fabio F. Oberweger, Mario Niedermeyer, Huemer Johannes, Markus Murschitz

机构 * AIT Austrian Institute of Technology Center for Vision, Automation & Control(奥地利技术研究院视觉、自动化与控制中心)

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

AI总结 PIRATR通过端到端3D点云检测框架,结合变换器实现参数化物体的6自由度姿态和属性估计,适用于机器人应用。

Comments 8 Pages, 11 Figures, Accepted at 2026 IEEE International Conference on Robotics & Automation (ICRA) Vienna

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03908 2026-02-05 cs.RO cs.CV 81%

Beyond the Vehicle: Cooperative Localization by Fusing Point Clouds for GPS-Challenged Urban Scenarios

超越车辆:通过融合点云进行协作定位以应对GPS挑战的都市场景

Kuo-Yi Chao, Ralph Rasshofer, Alois Christian Knoll

机构 * Technical University of Munich(慕尼黑技术大学) BMW Group(宝马集团)

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

AI总结 本文提出一种融合点云的协作定位方法,通过多传感器和多模态数据提升GPS不可靠城市环境中的定位精度和鲁棒性。

Comments 8 pages, 2 figures, Driving the Future Symposium 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16832 2026-02-04 cs.CV cs.RO eess.IV 81%

L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models

L2M-Reg:基于建筑级别的不确定性感知LiDAR点云与语义3D城市模型配准

Ziyang Xu, Benedikt Schwab, Yihui Yang, Thomas H. Kolbe, Christoph Holst

机构 * Chair of Engineering Geodesy, TUM School of Engineering and Design, Technical University of Munich(工程测量学教授会,技术大学慕尼黑工程与设计学院) Chair of Geoinformatics, TUM School of Engineering and Design, Technical University of Munich(地理信息学教授会,技术大学慕尼黑工程与设计学院)

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

AI总结 L2M-Reg提出一种基于平面的精细配准方法,解决建筑级别LiDAR点云与语义3D城市模型配准时的模型不确定性问题,实现更准确高效的配准效果。

Comments Accepted version by ISPRS Journal of Photogrammetry and Remote Sensing

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17427 2026-02-02 cs.CV cs.RO 81%

GMOR: A Lightweight Robust Point Cloud Registration Framework via Geometric Maximum Overlapping

GMOR: 一种通过几何最大重叠实现的轻量稳健点云配准框架

Zhao Zheng, Jingfan Fan, Long Shao, Hong Song, Danni Ai, Tianyu Fu, Deqiang Xiao, Yongtian Wang, Jian Yang

机构 * Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology(北京混合现实与先进显示工程研究中心,光学与 photonics 学院,北京理工大学) Zhengzhou Research Institute, Beijing Institute of Technology(郑州研究院,北京理工大学) School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学) School of Medical Technology, Beijing Institute of Technology(医学技术学院,北京理工大学)

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

AI总结 GMOR通过仅旋转BnB搜索和几何最大重叠方法,实现高效的点云配准,兼顾精度与效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01210 2026-01-14 cs.CV cs.RO 81%

Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission

实时LiDAR点云密集化用于低延迟空间数据传输

Kazuhiko Murasaki, Shunsuke Konagai, Masakatsu Aoki, Taiga Yoshida, Ryuichi Tanida

机构 * NTT Human Informatics Laboratories(NTT人机信息实验室)

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

AI总结 本文提出了一种基于卷积神经网络的实时LiDAR点云密集化方法,实现低延迟的3D场景生成与深度补全,效率比传统方法快15倍。

Journal ref 19th International Conference on Machine Vision Applications (MVA2025), IEICE Transactions on Information and Systems letter

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16265 2026-01-12 cs.CV cs.RO eess.IV physics.geo-ph 81%

Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images

基于TLS点云与嵌入式RGB图像融合的密集3D位移估计用于滑坡监测

Zhaoyi Wang, Jemil Avers Butt, Shengyu Huang, Tomislav Medic, Andreas Wieser

机构 * ETH Zurich, Institute of Geodesy(苏黎世联邦理工学院测绘与摄影测量研究所) Atlas optimization GmbH(Atlas优化公司)

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

AI总结 本文提出一种融合TLS点云与嵌入式RGB图像的粗到细方法,用于高精度滑坡位移估计,实现高空间覆盖度和准确性。

Comments Published in the International Journal of Applied Earth Observation and Geoinformation. 25 pages, 19 figures

Journal ref Int. J. Appl. Earth Obs. Geoinf., Vol. 146, 105093, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.02759 2026-01-07 cs.CV cs.RO 81%

Towards Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups

跨多样尺度、场景和传感器设置的零样本点云配准

Hyungtae Lim, Minkyun Seo, Luca Carlone, Jaesik Park

机构 * Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology(信息与决策系统实验室,麻省理工学院) Department of Computer Science and Engineering, Seoul National University(计算机科学与工程系,首尔国立大学)

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

AI总结 提出BUFFER-X框架,通过几何自举、分布感知采样和坐标归一化实现零样本点云配准,同时引入BUFFER-X-Lite提升效率,适用于多样场景和传感器设置。

Comments 18 pages, 15 figures. Extended version of our ICCV 2025 highlight paper [arXiv:2503.07940]. arXiv admin note: substantial text overlap with arXiv:2503.07940

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.23318 2025-12-30 cs.RO cs.CV 81%

PCR-ORB: Enhanced ORB-SLAM3 with Point Cloud Refinement Using Deep Learning-Based Dynamic Object Filtering

PCR-ORB: 基于深度学习的动态物体过滤改进的ORB-SLAM3

Sheng-Kai Chen, Jie-Yu Chao, Jr-Yu Chang, Po-Lien Wu, Po-Chiang Lin

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

AI总结 PCR-ORB通过深度学习优化点云细化,提升动态环境中ORB-SLAM3的定位与建图精度。

Comments 17 pages, 2 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07940 2025-12-24 cs.CV cs.RO eess.IV 81%

BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes

BUFFER-X:迈向多样化场景下的零样本点云配准

Minkyun Seo, Hyungtae Lim, Kanghee Lee, Luca Carlone, Jaesik Park

机构 * Laboratory for Information & Decision Systems(信息与决策系统实验室) Massachusetts Institute of Technology(麻省理工学院)

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

AI总结 BUFFER-X通过自适应体素大小、最远点采样和补丁尺度归一化,实现多样化场景下的零样本点云配准,无需先验信息或手动调参。

Comments 20 pages, 14 figures. Accepted as a highlight paper at ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05759 2025-12-08 cs.CV cs.RO 81%

Label-Efficient Point Cloud Segmentation with Active Learning

高效标注点云分割与主动学习

Johannes Meyer, Jasper Hoffmann, Felix Schulz, Dominik Merkle, Daniel Buescher, Alexander Reiterer, Joschka Boedecker, Wolfram Burgard

机构 * Department of Computer Science, University of Freiburg(弗赖堡大学计算机科学系) Fraunhofer IPM(弗劳恩霍夫IPM研究所) Institute for Sustainable Systems Engineering INATECH, University of Freiburg(可持续系统工程研究所INATECH,弗赖堡大学) Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg(技术大学纽伦堡计算机科学与人工智能系)

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

AI总结 本文提出了一种高效点云分割方法,通过二维网格和网络集成估计不确定性,实现更有效的主动学习。

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.15832 2025-12-08 cs.CV cs.RO 81%

Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Training

点-PNG:点云预训练中的条件伪负样本生成

Sutharsan Mahendren, Saimunur Rahman, Piotr Koniusz, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam

机构 * School of Electrical Engineering and Robotics, Queensland University of Technology (QUT), Brisbane, Australia(电气工程与机器人学学院,昆士兰理工大学(QUT),布里斯班,澳大利亚) School of Electrical Engineering(电气工程学院) Robotics, Queensland University of Technology (QUT), Brisbane, Australia(机器人学,昆士兰理工大学(QUT),布里斯班,澳大利亚) Australian National University(澳大利亚国立大学)

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

AI总结 Point-PNG通过生成条件伪负样本,提升点云预训练中对变换的敏感性和判别性表示,实现更丰富的变换线索捕捉。

Comments Accepted for publication in IEEE ACCESS

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03237 2025-12-04 cs.CV cs.GR 81%

LLM-Guided Material Inference for 3D Point Clouds

基于大语言模型的3D点云材料推断

Nafiseh Izadyar, Teseo Schneider

机构 * University of Victoria(维多利亚大学)

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

AI总结 本文提出基于大语言模型的3D点云材料推断方法,通过两阶段推理实现材料属性推断,验证了语言模型在连接几何推理与材料理解中的作用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08512 2025-12-02 cs.CV cs.RO 81%

Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression

我们是否已经看到了一切?基于场景图的深度点云压缩

Nikolaos Stathoulopoulos, Christoforos Kanellakis, George Nikolakopoulos

机构 * Robotics and AI Group, Department of Computer, Electrical and Space Engineering, Luleå University of Technology(机器人与人工智能组,计算机、电子与航天工程系,卢勒阿大学技术学院)

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

AI总结 本文提出基于场景图的深度点云压缩框架,通过语义感知编码和结构化解码实现高效压缩,保留结构和语义信息,并支持多机器人系统中的下游应用。

Comments Please cite published version. 8 pages, 6 figures

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 12, pp. 12477-12484, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.00803 2025-12-02 cs.CV cs.RO 81%

HiMo: High-Speed Objects Motion Compensation in Point Clouds

HiMo:点云中高速物体运动补偿

Qingwen Zhang, Ajinkya Khoche, Yi Yang, Li Ling, Sina Sharif Mansouri, Olov Andersson, Patric Jensfelt

机构 * Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology(机器人、感知与学习系,皇家理工学院) Scania Group(斯堪尼亚集团) Autonomous Transport Solutions Lab, Scania Group(自主运输解决方案实验室,斯堪尼亚集团)

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

AI总结 HiMo通过SeFlow++实时场景流估计器,解决点云中高速移动物体引起的运动失真问题,提升动态物体的几何一致性和视觉保真度。

Comments 15 pages, 13 figures, Published in Transactions on Robotics (Volume 41)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02687 2025-11-20 cs.CV cs.AI cs.LG cs.RO 81%

Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?

Miao Zhang, Sherif Abdulatif, Benedikt Loesch, Marco Altmann, Bin Yang

机构 * Robert Bosch GmbH, Corporate Research(罗伯特·博世有限公司,企业研究) University of Stuttgart, Institute of Signal Processing and System Theory(斯图加特大学,信号处理与系统理论研究所)

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

Comments 8 pages, 6 figures, 4 tables, accepted to 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025). Code: https://github.com/boschresearch/CAPMIX

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.24773 2025-10-30 cs.CV cs.LG cs.RO eess.IV 81%

Point-level Uncertainty Evaluation of Mobile Laser Scanning Point Clouds

Ziyang Xu, Olaf Wysocki, Christoph Holst

机构 * Chair of Engineering Geodesy, TUM School of Engineering(工程大地测量学教授职位,技术大学慕尼黑工程与设计学院) TUM Leonhard Obermeyer Center(技术大学慕尼黑Leonhard Obermeyer中心) CV4DT, University of Cambridge(Cambridge大学CV4DT)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05282 2025-10-27 cs.CV cs.AI cs.RO 81%

Rectified Point Flow: Generic Point Cloud Pose Estimation

Tao Sun, Liyuan Zhu, Shengyu Huang, Shuran Song, Iro Armeni

机构 * Stanford University(斯坦福大学) NVIDIA Research(NVIDIA研究)

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

Comments NeurIPS 2025 Camera-ready. Project page: https://rectified-pointflow.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19644 2025-10-13 cs.CV cs.RO 81%

The Impact of 2D Segmentation Backbones on Point Cloud Predictions Using 4D Radar

William Muckelroy, Mohammed Alsakabi, John Dolan, Ozan Tonguz

机构 * Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所) Electrical & Computer Engineering Department, University of Pittsburgh(匹兹堡大学电气与计算机工程系)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04362 2025-09-30 cs.RO cs.CV 81%

Learning Smooth State-Dependent Traversability from Dense Point Clouds

Zihao Dong, Alan Papalia, Leonard Jung, Alenna Spiro, Philip R. Osteen, Christa S. Robison, Michael Everett

机构 * Northeastern University(东北大学) University of Michigan, Ann Arbor(密歇根大学安娜堡分校) DEVCOM Army Research Laboratory (ARL)(国防部陆军研究实验室)

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

Comments 18 pages, 13 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23709 2025-09-30 cs.GR cs.CV cs.LG 81%

StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer

Zhenyu Shu, Jiajun Shen, Zhongui Chen, Xiaoguang Han, Shiqing Xin

机构 * School of Computer and Data Engineering, NingboTech University(计算机与数据工程学院,宁波科技学院) Ningbo Institute, Zhejiang University(浙江大学宁波院) School of Software Technology, Zhejiang University(浙江大学软件技术学院) School of Informatics, Xiamen University(厦门大学信息学院) Shenzhen Research Institute of Big Data, Chinese University of Hong Kong(香港中文大学深圳大数据研究院) School of Computer Science and Technology, ShanDong University(山东大学计算机科学与技术学院)

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

Journal ref IEEE Transactions on Visualization and Computer Graphics. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23703 2025-09-30 cs.GR cs.CV cs.LG 81%

DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph

Zhenyu Shu, Jian Yao, Shiqing Xin

机构 * School of Computer Science and Technology, Zhejiang Sci-Tech University(浙江科技学院计算机科学与技术学院) School of Computer and Data Engineering, NingboTech University(宁波工程学院计算机与数据工程学院) School of Computer Science and Technology, ShanDong University(山东大学计算机科学与技术学院)

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

Journal ref IEEE Transactions on Visualization and Computer Graphics, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18786 2025-09-25 cs.RO cs.CV 81%

Human-Interpretable Uncertainty Explanations for Point Cloud Registration

Johannes A. Gaus, Loris Schneider, Yitian Shi, Jongseok Lee, Rania Rayyes, Rudolph Triebel

机构 * University of Tübingen(图宾根大学) Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院) German Aerospace Center(德国航空航天中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14773 2025-09-19 cs.CV cs.RO 81%

A Real-Time Multi-Model Parametric Representation of Point Clouds

Yuan Gao, Wei Dong

机构 * School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05198 2025-09-08 cs.CV cs.AI cs.LG cs.RO 81%

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)

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02476 2025-09-04 cs.RO cs.CV eess.IV 81%

Point Cloud Recombination: Systematic Real Data Augmentation Using Robotic Targets for LiDAR Perception Validation

Hubert Padusinski, Christian Steinhauser, Christian Scherl, Julian Gaal, Jacob Langner

机构 * FZI Research Center for Information Technology(弗劳恩霍夫信息技术研究中心) ANavS GmbH - Advanced Navigation Solutions(ANavS GmbH-先进导航解决方案)

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

Comments Pre-print for IEEE IAVVC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18293 2025-08-27 cs.CV cs.AI cs.LG cs.RO 81%

Towards Training-Free Underwater 3D Object Detection from Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches

M. Salman Shaukat, Yannik Käckenmeister, Sebastian Bader, Thomas Kirste

机构 * Computer Science Department, University of Rostock(罗斯托克大学计算机科学系)

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

Comments 12 pages, 7 figures, submitted to IEEE Journal of Oceanic Engineering (IEEE-JOE)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17011 2025-08-26 cs.GR cs.CV 81%

A Survey of Deep Learning-based Point Cloud Denoising

Jinxi Wang, Ben Fei, Dasith de Silva Edirimuni, Zheng Liu, Ying He, Xuequan Lu

机构 * Department of Computer Science and Software Engineering, University of Western Australia(西澳大学计算机科学与软件工程系) Multimedia Lab, Department of Information Engineering, the Chinese University of Hong Kong(香港中文大学信息工程系多媒体实验室) School of Computer Science, China University of Geosciences (Wuhan)(中国地质大学(武汉)计算机科学学院) College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.13802 2025-08-22 cs.CV cs.RO 81%

TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather

Xiongwei Zhao, Congcong Wen, Xu Zhu, Yang Wang, Haojie Bai, Wenhao Dou

机构 * Grandzxw

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

Comments 15 pages, submit to IEEE TIP

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11618 2025-08-21 cs.CV cs.GR 81%

Real-time Neural Rendering of LiDAR Point Clouds

Joni Vanherck, Brent Zoomers, Tom Mertens, Lode Jorissen, Nick Michiels

机构 * Hasselt University(哈塞尔特大学) Digital Future Lab(数字未来实验室) Flanders Make 2 Research Foundation(弗拉芒制造2研究基金会)

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

Comments Accepted at Eurographics 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14358 2025-08-21 cs.CV cs.AI cs.RO 81%

Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation

Zhujun Li, Shuo Zhang, Ioannis Stamos

机构 * Graduate Center, CUNY(CUNY研究生中心) Hunter College, CUNY(CUNY霍普金斯学院) Weill Cornell Medicine(韦尔医学院)

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

Comments Accepted by ICCV 2025 Workshop on Recovering 6D Object Pose (R6D)

详情

展开后加载摘要…

URL PDF HTML 收藏