mlsanityData to 14 Oct 2026

PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

arXiv 1903.05711 ↗First posted 13 Mar 2019cs.CVcited by 233

Not on the map. Why?

Abstract (arXiv)

PointNet has revolutionized how we think about representing point clouds. For classification and segmentation tasks, the approach and its subsequent extensions are state-of-the-art. To date, the successful application of PointNet to point cloud registration has remained elusive. In this paper we argue that PointNet itself can be thought of as a learnable "imaging" function. As a consequence, classical vision algorithms for image alignment can be applied on the problem - namely the Lucas & Kanade (LK) algorithm. Our central innovations stem from: (i) how to modify the LK algorithm to accommodate the PointNet imaging function, and (ii) unrolling PointNet and the LK algorithm into a single trainable recurrent deep neural network. We describe the architecture, and compare its performance against state-of-the-art in common registration scenarios. The architecture offers some remarkable properties including: generalization across shape categories and computational efficiency - opening up new paths of exploration for the application of deep learning to point cloud registration. Code and videos are available at https://github.com/hmgoforth/PointNetLK.

Key facts. Cited by 233 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 53; 2022: 57; 2023: 49; 2024: 28; 2025: 28; 2026: 18.

233 papers.

Sort:

By area:

  1. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  2. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  3. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  4. 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 97
  5. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 96
  6. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  7. 2021A comprehensive survey on point cloud registrationcited by 84
  8. 20233D Registration with Maximal Cliquescited by 84
  9. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 84
  10. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  11. 2021LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAMcited by 67
  12. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
38 more
  1. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  2. 2021OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registrationcited by 51
  3. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 48
  4. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  5. 2022CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondencecited by 44
  6. 2022nerf2nerf: Pairwise Registration of Neural Radiance Fieldscited by 39
  7. 2021Accurate Point Cloud Registration with Robust Optimal Transportcited by 38
  8. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  9. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 33
  10. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  11. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  12. 2021Bootstrap Your Own Correspondencescited by 27
  13. 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registrationcited by 27
  14. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  15. 2021Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representationscited by 24
  16. 2022Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transportcited by 24
  17. 2021ReAgent: Point Cloud Registration using Imitation and Reinforcement Learningcited by 23
  18. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20
  19. 2022Reliable Inlier Evaluation for Unsupervised Point Cloud Registrationcited by 20
  20. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 19
  21. 2023CHAMMI: A benchmark for channel-adaptive models in microscopy imagingcited by 18
  22. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  23. 2021DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusioncited by 17
  24. 2022ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairscited by 17
  25. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  26. 2021FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registrationcited by 14
  27. 2023PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registrationcited by 14
  28. 2022MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real Worldcited by 13
  29. 2023PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometrycited by 13
  30. 2021DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registrationcited by 12
  31. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  32. 2022Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformationcited by 12
  33. 2023Density-invariant Features for Distant Point Cloud Registrationcited by 12
  34. 20213D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learningcited by 11
  35. 2023TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performancecited by 11
  36. 2023G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Modelcited by 11
  37. 2021Matching Point Sets with Quantum Circuit Learningcited by 10
  38. 2021Real-time multimodal image registration with partial intraoperative point-set datacited by 10

50 most cited of 233 All 233 (JSON)