mlsanityData to 14 Oct 2026

A comprehensive survey on point cloud registration

arXiv 2103.02690 ↗First posted 3 Mar 2021cs.CVcited by 84

Not on the map. Why?

Abstract (arXiv)

Registration is a transformation estimation problem between two point clouds, which has a unique and critical role in numerous computer vision applications. The developments of optimization-based methods and deep learning methods have improved registration robustness and efficiency. Recently, the combinations of optimization-based and deep learning methods have further improved performance. However, the connections between optimization-based and deep learning methods are still unclear. Moreover, with the recent development of 3D sensors and 3D reconstruction techniques, a new research direction emerges to align cross-source point clouds. This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight. This survey also builds a new benchmark to evaluate the state-of-the-art registration algorithms in solving cross-source challenges. Besides, this survey summarizes the benchmark data sets and discusses point cloud registration applications across various domains. Finally, this survey proposes potential research directions in this rapidly growing field.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Builds on 36 of its 126 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

36 of 126 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  3. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  4. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  5. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  6. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  7. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  8. 2020Deep Global Registrationcited by 229
  9. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  10. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 182
  11. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  12. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
24 more
  1. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  2. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  3. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  4. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 109
  5. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 103
  6. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  7. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  8. 2020Deep Graph Matching Consensuscited by 85
  9. 2019DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registrationcited by 77
  10. 2017Guaranteed Outlier Removal for Point Cloud Registration with Correspondencescited by 62
  11. 2017Learning Compact Geometric Featurescited by 45
  12. 2019A Polynomial-time Solution for Robust Registration with Extreme Outlier Ratescited by 38
  13. 2019SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondencescited by 26
  14. 20193D Local Features for Direct Pairwise Registrationcited by 26
  15. 2018Extreme Relative Pose Estimation for RGB-D Scans via Scene Completioncited by 22
  16. 2017DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problemscited by 20
  17. 2019AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objectscited by 12
  18. 2016A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structurescited by 11
  19. 2016Alternating Direction Graph Matchingcited by 9
  20. 2016A coarse-to-fine algorithm for registration in 3D street-view cross-source point cloudscited by 8
  21. 2019Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinementcited by 8
  22. 2019Non-Rigid Point Set Registration Networkscited by 8
  23. 2019Learning to Fuse Local Geometric Features for 3D Rigid Data Matchingcited by 2
  24. 2019Procrustes registration of two-dimensional statistical shape models without correspondencescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 18; 2023: 19; 2024: 22; 2025: 14; 2026: 5.

84 papers.

Sort:

By area:

  1. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  2. 2021Accurate Point Cloud Registration with Robust Optimal Transportcited by 38
  3. 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3Dcited by 33
  4. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  5. 2022Sliced Optimal Partial Transportcited by 20
  6. 2022PD-Flow: A Point Cloud Denoising Framework with Normalizing Flowscited by 19
  7. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 19
  8. 2024One-Shot Imitation Learning with Invariance Matching for Robotic Manipulationcited by 18
  9. 2023One-shot Imitation Learning via Interaction Warpingcited by 16
  10. 2022ARCS: Accurate Rotation and Correspondence Searchcited by 15
  11. 2023PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registrationcited by 14
  12. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
38 more
  1. 2021IMFNet: Interpretable Multimodal Fusion for Point Cloud Registrationcited by 12
  2. 2023Rearrangement Planning for General Part Assemblycited by 12
  3. 2022Self-Supervised Point Cloud Registration with Deep Versatile Descriptorscited by 10
  4. 2023CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognitioncited by 10
  5. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matchingcited by 9
  6. 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapescited by 8
  7. 2022GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejectioncited by 7
  8. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  9. 2022UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registrationcited by 6
  10. 2022PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registrationcited by 6
  11. 2024Deep Learning-based Point Cloud Registration for Augmented Reality-guided Surgerycited by 6
  12. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  13. 2021HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameterscited by 5
  14. 2021COTReg:Coupled Optimal Transport based Point Cloud Registrationcited by 5
  15. 2022SARNet: Semantic Augmented Registration of Large-Scale Urban Point Cloudscited by 5
  16. 2025Progressive Correspondence Regenerator for Robust 3D Registrationcited by 5
  17. 2025Splat and Replace: 3D Reconstruction with Repetitive Elementscited by 5
  18. 2022SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloudcited by 4
  19. 2022SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimationcited by 4
  20. 2023Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networkscited by 4
  21. 2023Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud Registrationcited by 4
  22. 2024NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detectioncited by 4
  23. 2024Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matchingcited by 4
  24. 2024Cross-PCR: A Robust Cross-Source Point Cloud Registration Frameworkcited by 4
  25. 2022Centroid Distance Keypoint Detector for Colored Point Cloudscited by 3
  26. 2023FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimizationcited by 3
  27. 2024VRHCF: Cross-Source Point Cloud Registration via Voxel Representation and Hierarchical Correspondence Filteringcited by 3
  28. 2024GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking Systemcited by 3
  29. 2024Deep Loss Convexification for Learning Iterative Modelscited by 3
  30. 2025Fully-Geometric Cross-Attention for Point Cloud Registrationcited by 3
  31. 2022LiDAR Point--to--point Correspondences for Rigorous Registration of Kinematic Scanning in Dynamic Networkscited by 2
  32. 2022An approach to robust ICP initializationcited by 2
  33. 2023SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registrationcited by 2
  34. 2023Partial Transport for Point-Cloud Registrationcited by 2
  35. 2023Decodable and Sample Invariant Continuous Object Encodercited by 2
  36. 2024YOCO: You Only Calibrate Once for Accurate Extrinsic Parameter in LiDAR-Camera Systemscited by 2
  37. 20243D Registration in 30 Years: A Surveycited by 2
  38. 2025DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformationcited by 2

50 most cited of 84 All 84 (JSON)