Point Cloud Surface Reconstruction

Ask about this topic

Overview

The field studies how to infer a usable surface from 3D points collected by sensors, scans, or multiple images, enabling tasks such as measurement, mapping, and object modeling. Common approaches include implicit signed or unsigned distance fields, learned and generative shape models, and explicit mesh methods such as Poisson reconstruction and ball pivoting; some also use visibility, normals, or temporal observations as constraints. Methods are evaluated on object and scene benchmarks, as well as LiDAR, photogrammetry, and dynamic-scanning settings, using measures of geometric accuracy, completeness, smoothness, and runtime. A central tension is reconstructing fine or thin geometry from sparse, noisy, and occluded data without sacrificing robustness, scalability, or computational efficiency.

Latest papers

CardsList

35 papers8 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

  1. A Singularity Avoiding Track Model for Race Car Optimization

    Oct 27, 2026Adwait Verulkar, Behzad Danaei, Srikanth Sivaramakrishnan +1Curvature-Aware OptimizationPoint Cloud Surface Reconstruction

    General Motors, USA

  2. Neural Implicit Energy Optimization for LiDAR Mapping

    Oct 20, 2026Hrishikesh Viswanath, Md Ashiqur Rahman, Chi Lin +2Large-Scale 3D ReconstructionPoint Cloud Surface Reconstruction

    Purdue University, USA · DEVCOM, Army Research Laboratory, USA

  3. Reliability-Aware Reconstruction of V-Shaped Surfaces with a Low-Cost Multi-Zone SPAD Sensor

    Oct 20, 2026Yohanssen PratamaDepth EstimationPoint Cloud Surface Reconstruction

    Institute for International Strategy and Emerging Technologies, Tokyo International University, 1-13-1 Matoba-Kita, Kawagoe, 350-1197, Japan

  4. Surface Reconstruction from Range Scans Under Visibility Constraints

    Oct 13, 2026Gabriel Lenain, Edmond Boyer, Jean Ponce3D ReconstructionPoint Cloud Surface Reconstruction

    Inria Paris · École normale supérieure - PSL · Univ. Grenoble Alpes, Inria +2

  5. PCAsplat: Gaussian Splatting with Local PCA Regularization

    Oct 7, 2026Vitor Matias, Filipe Nascimento, Kiyohiro Nakayama +63D Gaussian SplattingPoint Cloud Surface Reconstruction

    Universidade de São Paulo · Stanford University · UFRPE +1

  6. A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction

    Oct 5, 2026Xiaozhen Ma, Zhao Tang, Hanbin Lai +2Point Cloud Completion3D Reconstruction

  7. R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments

    Oct 4, 2026Xudong Yuan, Ruyun Xu, Jingtai Yang +13D ReconstructionPoint Cloud Surface Reconstruction

    School of Mathematics and Statistics, Changchun University of Science and Technology, Changchun, China.

  8. CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts

    Sep 29, 2026Tianhang Pan, Xuanhao Wang, Yiwen Pang +4Point Cloud Surface ReconstructionVision-Language-Action Models

    Southeast University, Nanjing, China · National Center of Technology Innovation for EDA, Nanjing, China

  9. Projective Normal Fields: A Convex Optimization Method for Constructing Smooth UDFs

    Sep 28, 2026Jiayi Kong, Chen Zong, Fei Hou +33D ReconstructionSurface Normal Estimation

    S-Lab Nanyang Technological University Singapore · College of Mathematics Nanjing University of Aeronautics and Astronautics China · Institute of Software Chinese Academy of Sciences China +2

  10. Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity

    Sep 22, 2026Wei Zhou, Xinzhe Shi, Xingxing Hao +43D ReconstructionSingle-View 3D Reconstruction

    Northwest University, Xi’an, China · Nanyang Technological University, Singapore

  11. NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction

    Sep 17, 2026Qingde Li, Qingqi Hong, Zihan Li +13D ReconstructionPoint Cloud Surface Reconstruction

    Computer Science, School of Digital and Physical Sciences, University of Hull, HU6 7RX, UK · The Institute of Artificial Intelligence, Xiamen University, Xiamen, China · Department of Bioengineering, University of Washington, Seattle, WA, USA +1

  12. Gaussian Linear Functional Manifold Method for Massive Point Cloud Data

    Sep 4, 2026Hong Zhao, Tonglin Zhang, Baijian Yang +2Point Cloud Surface Reconstruction3D Reconstruction

    School of Applied and Creative Computing, Purdue University, West Lafayette, IN, USA · Department of Statistics, Purdue University, West Lafayette, IN, USA · Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA

  13. Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds

    Sep 2, 2026Mohammad Waquas Usmani, Susmit Shannigrahi, Michael ZinkPoint Cloud Surface Reconstruction

    University of Massachusetts Amherst Massachusetts, USA · Tennessee Technological University Tennessee, USA

  14. 3D Point Cloud from Close-Range Photogrammetry for Defect Characterisation of Rubberised Concrete

    Aug 21, 2026Jiacheng Liu, Mohammed Alnahhal, Ailar Hajimohammadi +33D ReconstructionPoint Cloud Surface Reconstruction

    School of Civil and Environmental Engineering, University of New South Wales, Sydney, NSW 2052, Australia · Dept. of Engineering, Università degli Studi della Campania Luigi Vanvitelli, via Roma 29, 81031, Aversa (CE), Italy

  15. Point-Based 3D Reconstruction from Sparse Views under Known Illumination

    Aug 20, 2026Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad +3Sparse-View 3D ReconstructionPoint Cloud Surface Reconstruction

    Visual Analysis & Perception Lab, Aalborg University · Centre for Software Technology, University of Southern Denmark · Pioneer Centre for Artificial Intelligence +2

  16. Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds

    Jul 30, 2026Hongbo Li, Haikuan Zhu, Xiaohu Guo +33D ReconstructionPoint Cloud Learning

    Department of Computer Science, Wayne State University, Detroit, USA · Department of Computer Science, Univeristy of Texas at Dallas, USA · Department of Computer Science & Engineering, Texas A&M University, USA

  17. CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement

    Jul 21, 2026Zhihao Yang, Zhiyu Xiang, Peng Xu +5Point Cloud Surface Reconstruction3D Object Detection

    Zhejiang University, Hangzhou, China · Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing, Hangzhou, China · China Jiliang University, Hangzhou, China

  18. Points as Tori: Fast Pointwise Signed Distance for Point Clouds

    Jul 18, 2026Nicole Feng, Ioannis Gkioulekas, Keenan CraneSigned Distance Functions3D Reconstruction

    Carnegie Mellon University, USA · Roblox, USA

  19. IBPA: Real-time Free-form Manifold Mesh Reconstruction via Incremental Ball Pivoting with Integrated Hole Detection

    Jul 13, 2026Mauhing Yip, Mohit Singh, Kostas Alexis +23D Mesh GenerationStreaming 3D Reconstruction

    Department of Engineering Cybernetics, NTNU, O. S. Bragstads Plass 2D, Trondheim, 7034, Norway · SINTEF Ocean, Brattørkaia 17c, Trondheim, 7010, Norway

  20. City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion

    Jul 4, 2026Liang Han, Wenyuan Zhang, Junsheng Zhou +23D Gaussian Splatting3D Reconstruction

    School of Software, Tsinghua University, Beijing, China · Department of Computer Science, Wayne State University, Detroit, USA

  21. Learned Radius Estimation for UDF-Based Point Cloud Reconstruction

    Jun 17, 2026Eito Ogawa, Hiroshi Watanabe3D ReconstructionPoint Cloud Surface Reconstruction

    Graduate School of FSE · Waseda University · Tokyo, Japan

  22. Point Cloud Upsampling through Patch-based Frequency Superposition

    Jun 12, 2026Marina Ritthaler, Azhar Hussian, Vasileios Belagiannis +13D ReconstructionPoint Cloud Learning

    Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-University Erlangen-Nuremberg Erlangen, Germany

  23. Hierarchical Space Partition for Surface Reconstruction

    Jun 3, 2026Minjie Tang, Xiangfei Li3D Mesh Generation3D Reconstruction

    Independent Researcher · Huazhong University of Science and Technology

  24. DisFlow: Scene Flow from Distance Field for Object Pose, Velocity Tracking, and Dynamic Object Reconstruction

    Jun 1, 2026Lan Wu, Sheila Sutjipto, Jennifer Wakulicz +1Scene Flow EstimationVisual Object Tracking

    Robotics Institute, University of Technology Sydney, Ultimo, NSW 2007, Australia

  25. ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects

    May 28, 2026Deokmin Hwang, Minseok Song, Daehyung ParkImplicit Neural Representations3D Reconstruction

    School of Computing, Korea Advanced Institute of Science and Technology, Korea

  26. Metric--Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds

    May 25, 2026Jiayi Kong, Xuhui Chen, Chen Zong +4Signed Distance Functions3D Reconstruction

    S-Lab, Nanyang Technological University, Singapore · Key Laboratory of System Software (CAS), Institute of Software, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China +3

  27. Medial Axis Aware Learning of Signed Distance Functions

    Apr 15, 2026Samuel Weidemaier, Christoph Norden-Smoch, Martin RumpfSigned Distance FunctionsPoint Cloud Surface Reconstruction

    Institute for Numerical Simulation, University of Bonn

  28. RAIN-FIT: Learning of Fitting Surfaces and Noise Distribution from Large Data Sets

    Apr 3, 2026Omar M. Sleem, Sahand Kiani, Constantino M. LagoaPoint Cloud Surface Reconstruction3D Reconstruction

    Kyocera International, Inc. · Pennsylvania State University

  29. Review and Evaluation of Point-Cloud based Leaf Surface Reconstruction Methods for Agricultural Applications

    Apr 2, 2026Arif Ahmed, Parikshit MainiPoint Cloud Surface Reconstruction3D Reconstruction

    Department of Computer Science and Engineering, University of Nevada, Reno, Reno 89557, Nevada, USA

  30. Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing

    Apr 1, 2026Ryo Yoshida, Takami Sato, Wenlun Zhang +7Point Cloud LearningPoint Cloud Surface Reconstruction

    Keio University, Yokohama, Japan · Sony Semiconductor Solutions, Atsugi, Japan · Hainan University, Haikou, China