Point Cloud Compression

Ask about this topic

Overview

Point cloud compression studies how to encode 3D geometry and attributes such as color or LiDAR reflectance with fewer bits, for uses including robotics, autonomous driving, streaming, and dynamic scenes. Methods include octree and transform codecs such as G-PCC, predictive and entropy coding, learned neural representations, and temporal prediction across frames. Work also explores scalable and progressive bitstreams, wireless transmission, and compression that preserves downstream perception quality. A central challenge is balancing reconstruction quality and task accuracy against bitrate, latency, compute cost, and robustness to bandwidth changes or packet loss.

Latest papers

CardsList

22 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression

    Sep 28, 2026Yueru Chen, Pengpeng Yu, Dingquan Li +3Point Cloud Compression

    Pengcheng Laboratory, Shenzhen, China · Sun Yat-sen University, Shenzhen, China · Peking University, Shenzhen, China +1

  2. Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds

    Sep 26, 2026Manlin Yao, Jiabin Liu, Guan Wang +2Point Cloud CompressionImplicit Neural Representations

  3. CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting

    Sep 2, 2026Kyungdae Park, Chae Eun RheeDynamic Gaussian SplattingGaussian Splatting

    Department of Artificial Intelligence Semiconductor Engineering, Hanyang University, Seoul 04763, South Korea · Department of Electronic Engineering, Hanyang University, Seoul 04763, South Korea

  4. Geometry-Based Compression of Plenoptic Point Clouds

    Aug 11, 2026Davi R. Freitas, Gustavo L. Sandri, Ricardo L. de QueirozPoint Cloud Compression

    Inria - Rennes Bretagne-Atlantique Rennes, France · Instituto Federal de Bras´ılia Bras´ılia, Brazil · Universidade de Bras´ılia Bras´ılia, Brazil

  5. Proteus: A Truncation-Robust Entropy Model for Progressive LiDAR Compression

    Aug 1, 2026Yihan Qiu, Xiaodong Lin, Baoquan Zhao +2Point Cloud CompressionEntropy Modeling

    Peking University · Sun Yat-sen University

  6. Motion Estimation Techniques for Volumetric Video Attribute Compression

    Jul 3, 2026Haoran Hong, Eduardo Pavez, Antonio Ortega +2Point Cloud Compression

    University of Southern California, 3740 McClintock Ave., Los Angeles, CA 90089-2564, USA · KDDI Research, Inc., 2-1-15 Ohara, Fujimino, Saitama, 356-8502, Japan

  7. GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds

    Jun 4, 2026Rajrup Ghosh, Haodong Wang, Haoran Hong +63DGS Compression3D Gaussian Splatting

    University of Southern California

  8. Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression

    May 18, 2026Chang Sun, Hui Yuan, Shiqi Jiang +3Point Cloud CompressionPredictive Coding

    School of Control Science and Engineering, Shandong University, Jinan 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250061, China · School of Computer Science and Technology, Shandong University, Qingdao, 266237, China +1

  9. PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression

    May 2, 2026Jiahao Zhu, Kang You, Dandan Ding +1Point Cloud CompressionAirborne Laser Scanning

    School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China. · School of Electronic Science and Engineering, Nanjing University, Nanjing, China.

  10. TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

    Apr 30, 2026Xiumei Li, Alexander Kopte, André KaupPoint Cloud CompressionRate-Distortion Optimization

    Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen, Germany

  11. Octree-based Learned Point Cloud Geometry Compression: A Lossy Perspective

    Mar 30, 2026Kaiyu Zheng, Wei Gao, Huiming ZhengPoint Cloud Compression

    School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China

  12. SAFT: Sensitivity-Aware Filtering and Transmission for Adaptive 3D Point Cloud Communication over Wireless Channels

    Mar 27, 2026Huda Adam Sirag Mekki, Hui Yuan, Mohanad M. G. Hassan +2Joint Source-Channel CodingWireless Communications

    School of Control Science and Engineering, Shandong University, Ji’nan, 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Ji’nan, 250061, China · School of Computer Science and Technology, Shandong University, Qingdao, China

  13. DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds

    Mar 27, 2026Pan Zhao, Hui Yuan, Chang Sun +3Point Cloud Compression

    School of Control Science and Engineering, Shandong University, Jinan 250061, China, and also with the Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Ji’nan, 250061, China · School of Engineering, Infrastructure and Sustainability De Montfort University, LE1 9BH Leicester, UK · Department of Computing and Decision Science, Lingnan University, Hong Kong

  14. Towards Practical Lossless Neural Compression for LiDAR Point Clouds

    Mar 26, 2026Pengpeng Yu, Haoran Li, Runqing Jiang +4Point Cloud Compression

    Sun Yat-sen University, China · Pengcheng Laboratory, China

  15. LiZIP: An Auto-Regressive Compression Framework for LiDAR Point Clouds

    Mar 24, 2026Aditya Shibu, Kayvan Karim, Claudio ZitoPoint Cloud CompressionPredictive Coding

    MACS, Heriot Watt University, Dubai, United Arab Emirates

  16. D-Compress: Detail-Preserving LiDAR Range Image Compression for Real-Time Streaming on Resource-Constrained Robots

    Mar 14, 2026Shengqian Wang, Chang Tu, He ChenPoint Cloud CompressionRate-Distortion Optimization

    Department of Information Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong, China.

  17. Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception

    Feb 25, 2026Sheng Xu, Enshu Wang, Hongfei Xue +6Communication-Efficient Collaborative PerceptionCooperative Perception

    School of Cyber Science and Engineering, Wuhan University, China · University of North Carolina at Charlotte, USA · Wuhan University of Technology, China +2

  18. Hybrid-PCGC: Hybrid Point Cloud Geometry Compression Bridging Generalization-based Model and Implicit Neural Representation

    Feb 25, 2026Wenjie Huang, Qi Yang, Shuting Xia +3Point Cloud CompressionImplicit Neural Representations

    Shanghai Jiao Tong University · University of Missouri-Kansas City

  19. Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding

    Sep 10, 2025Tam Thuc Do, Philip A. Chou, Gene CheungPoint Cloud CompressionRate-Distortion Optimization

    department of EECS, York University, 4700 Keele Street, Toronto, M3J 1P3, Canada

  20. Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds

    Jun 13, 2025Filippo Bragato, Michael Neri, Paolo Testolina +23D Object DetectionLidar-Based 3D Object Detection

    Department of Information Engineering, University of Padova. Padova, Italy. · Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland · Institute for the Wireless Internet of Things, Northeastern University, Boston, MA, USA

  21. Squeeze3D: Extreme Neural Compression with Latent Space Bridging

    Jun 9, 2025Rishit Dagli, Yushi Guan, Sankeerth Durvasula +2Point Cloud Compression

    University of Toronto

  22. Efficient LiDAR Reflectance Compression via Scanning Serialization

    May 14, 2025Jiahao Zhu, Kang You, Dandan Ding +1Point Cloud Compression

    School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China · School of Electronic Science and Engineering, Nanjing University, Nanjing, China