Point Cloud Learning

Ask about this topic

Overview

Point cloud learning studies how to extract shape, spatial relationships, and motion from unordered, irregular 3D samples that may be sparse, noisy, or incomplete. Methods range from point and graph networks to sparse convolutions, transformers, state-space models, and geometrically equivariant architectures; self-supervised and multimodal pretraining aim to make their representations useful across tasks and sensors. Applications include classification, segmentation, reconstruction, registration, tracking, robotics, and 4D motion understanding, with benchmarks spanning objects, indoor scenes, and large-scale LiDAR. A central challenge is balancing accuracy and transfer across changes in density, viewpoint, and sensor with the memory, computation, and data needed for practical deployment.

Latest papers

CardsList

159 papers14 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

  1. SAGE: Semantic-Augmented Geometric Experts for Point Cloud Registration

    Oct 27, 2026Tomoyasu Shimada, Kazuhiko Murasaki, Shoichiro Takeda +4Point Cloud RegistrationPoint Cloud Learning

    NTT, Inc.

  2. Register Anything Model for Generalizable and Robust Point Cloud Registration

    Oct 20, 2026Zheng Qin, Junhua Xi, Yan Huang +5Point Cloud RegistrationPoint Cloud Learning

    Defense Innovation Institute, Academy of Military Sciences, China · College of Computer Science and Technology, National University of Defense Technology, China · College of Data Intelligence, Information Support Force Engineering University, China +1

  3. Degree Bounds for Separating Polynomial and Neural Invariants for Point Clouds

    Oct 19, 2026Snir Hordan, Harm Derksen, Mircea Petrache +1Point Cloud LearningEquivariant Neural Networks

    Technion – Israel Institute of Technology · Northeastern University · Pontificia Universidad Católica de Chile

  4. Semi-supervised learning on singular data sets

    Oct 18, 2026Guillaume ValetteSemi-Supervised LearningPoint Cloud Learning

  5. SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing

    Oct 15, 2026Inseok Kong, Geunyoung Jung, Jiyoung JungTest-Time AdaptationToken Pruning

    Department of Geo Informatics, University of Seoul, South Korea · Department of Artificial Intelligence, University of Seoul, South Korea

  6. ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling

    Oct 15, 2026Yuang Liu, Zhi Zuo, Zhengkai Zhao +4Point Cloud LearningFlow Matching

    Nanjing University of Aeronautics and Astronautics · Weidian Corporation · Lingnan University

  7. SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning

    Oct 15, 2026Jongann Lee, Sun Woo Park, Yun Young ChoiSelf-Supervised Point Cloud LearningPoint Cloud Learning

    Max Planck Institute of Mathematics Bonn, Germany · SolverX Seoul, Republic of Korea

  8. Reducing the Gap Between Spatial and Space-Filling Curve Neighbors in 3D Point Cloud Segmentation

    Oct 14, 2026Konan Sasaki, Junya Komori, Kazuhiro Hotta3D Point Cloud SegmentationPoint Cloud Learning

    Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya, Aichi 468-8502, Japan · Asia Air Survey Co., Ltd., Shinyuri 21 Bldg., 1-2-2 Manpukuji, Asao-ku, Kawasaki, Kanagawa 215-0004, Japan

  9. PointWalker: Mapless Quadruped Locomotion Directly From Raw LiDAR Point Clouds

    Oct 11, 2026Sicen Li, Zhen Chu, Chao Li +3Quadruped LocomotionLegged Robotics

    College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China · Yunshenchu Technology Co., Ltd., Hangzhou, China · Hangzhou Public Library, Hangzhou, China +1

  10. Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation

    Oct 8, 2026Kanglin Qu, Pan Gao, Qun Dai +1Point Cloud Learning3D Representation Learning

    College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics · Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education · School of Mathematical Sciences, Beijing University of Posts and Telecommunications

  11. GUARD: Geometric Uncertainty-Aware Point Cloud Denoising and Segmentation for Robotic Hard Disk Drive Disassembly

    Oct 6, 2026Zuoxu Wang, Xiao LiangPoint Cloud DenoisingPoint Cloud Learning

    Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX 77843 USA

  12. Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane

    Oct 6, 2026George Sideris, Lucas Bessai, Heshan Fernando +3Robotic GraspingSim-to-Real Transfer

    McGill University, Montreal, QC, Canada. · FPInnovations, Pointe-Claire, QC, Canada.

  13. DiFF: Doppler-informed Flow Matching for Human Motion Flow

    Sep 30, 2026Kai Wang, Mingle ZhaoFlow MatchingScene Flow Estimation

  14. Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation

    Sep 29, 2026Yuzhen He, Sara HomscheidPoint Cloud LearningNon-Rigid Shape Correspondence

    Mannheim Institute for Intelligent Systems in Medicine (MIISM) Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany

  15. EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation

    Sep 29, 2026Abu Hanif Muhammad Syarubany, Chang D. YooHumanoid Loco-ManipulationPoint Cloud Learning

    School of Electrical Engineering Korea Advanced Institute of Science & Technology (KAIST) Daejeon, Republic of Korea

  16. ReLoc: Rethinking Scene Coordinate Regression Architecture for Robust Outdoor LiDAR-based Localization

    Sep 27, 2026Heejoon Moon, Yurim Cho, Je Hyeong HongScene Coordinate RegressionPoint Cloud Learning

    Department of Artificial Intelligence, Hanyang University · Department of Electronic Engineering, Hanyang University

  17. KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization

    Sep 23, 2026Shuxin Cao, Liquan Wang, Masoud Moghani +2Point Cloud LearningGeneralization in Robotic Manipulation

    Georgia Institute of Technology · University of Toronto

  18. PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation

    Sep 23, 2026Hantao Ye, Ross Worobel, Zhuoli Xie +4World Models for RoboticsRobotic Manipulation

    University of Minnesota, Minneapolis, MN 55455, USA

  19. UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains

    Sep 20, 2026Sicen Li, Zhen Chu, Chao Li +2Humanoid Robot LocomotionPoint Cloud Learning

    College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China · Yunshenchu Technology Co., Ltd., Hangzhou, China · Zhejiang Key Laboratory of Additive Manufacturing Technology and Equipment, Hangzhou, China

  20. Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion

    Sep 18, 2026Hang Cheng, Yan Chen, Mingyu Fan +1Few-Shot LearningPoint Cloud Learning

    Tsinghua Shenzhen International Graduate School, Tsinghua University

  21. FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

    Sep 17, 2026Kevin Qu, Tao Sun, Massimiliano Viola +5Articulated Object Reconstruction3D ViTs

    Stanford University · ETH Zürich

  22. GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model

    Sep 17, 2026Zixiang Ai, Zhenyu Cui, Yufei Guo +4Point Cloud LearningVision Foundation Model Adaptation

    Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China · Intelligent Science and Technology Academy of CASIC, Beijing 100041, China · Institute of Software, Chinese Academy of Sciences, Beijing 100190, China +1

  23. Instance Segmentation and Fine-grained Classification for Urban Buildings with Adaptive Region Dividing and Spatially-Supervised Contrastive Learning

    Sep 17, 2026Weiyuan Zhang, Qi Zhang, Hui HuangContrastive LearningPoint Cloud Classification

    Guangdong Provincial Key Laboratory of Visual Media and Multidimensional Intelligence, College of Computer Science and Software Engineering, Shenzhen University

  24. PC2^2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devices

    Sep 13, 2026Yutong Gu, Yingxi Xie, Kejin Huang +4Point Cloud Anomaly DetectionAnomaly Detection

    Shenzhen University WeBank Institute of Finance, Shenzhen University, Shenzhen 518060, China · School of Computer Science, Wuhan University, Wuhan 430072, China · Shenzhen Audencia Financial Technology Institute, Shenzhen University, Shenzhen 518060, China +2

  25. Semantic Privacy Protection with Utility Preservation for 3D Point Clouds

    Sep 12, 2026Jinchang zhang, Jiakai Lin, David Crandall +1Privacy-Preserving MLPoint Cloud Learning

    Department of Computer Science, Indiana University, Bloomington, IN, 47405, USA.

  26. Partition-Invariant Tuning for 3D Scene Understanding

    Sep 11, 2026Hongqiang Lin, Tianle Wang, Shuiwang Li +4Point Cloud LearningParameter-Efficient Fine-Tuning

    ZJU · GUT · THU +3

  27. Beyond Gait: Person Identification from Millimeter-Wave Point Clouds Across Activities of Daily Living

    Sep 8, 2026Xilai Wang, Zixiong Han, Saad Rhanmouni +3Biometric IdentificationPoint Cloud Learning

    Computational Analysis and Applications Research Group, University of Ottawa, Ottawa, ON K1N 6N5, Canada

  28. Heat Field Signatures: From Point Clouds to Smooth Geometry

    Sep 7, 2026Yuanqing Wang, Yapeng Tian, Baris CoskunuzerPoint Cloud LearningGeometric Representation Learning

    Dept. of Math. Sciences University of Texas at Dallas Richardson, TX, USA · Dept. of Computer Science University of Texas at Dallas Richardson, TX, USA

  29. EquiGQNet: Fast Grasp Quality Evaluation via Shared Equivariant Point Cloud Encoding

    Sep 7, 2026Sungwon Seo, Jaeseog Won, Jiyou Shin +5Robotic GraspingPoint Cloud Learning

    The authors are with the Faculty of Mechanical Engineering, Sungkyunkwan University, Suwon 16419, South Korea · The authors are with the Faculty of Intelligent Robotics, Sungkyunkwan University, Suwon 16419, South Korea

  30. Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics

    Sep 1, 2026Samuel Young, César Jesús-Valls, Kazuhiro TeraoSelf-Supervised Pre-TrainingPoint Cloud Learning

    Stanford University · Stanford, CA 94305 · European Organization for Nuclear Research (CERN) +3