mlsanityData to 7 Oct 2026

Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks

arXiv 2306.04701 ↗First posted 7 Jun 2023cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Point cloud registration is a fundamental problem in computer vision that aims to estimate the transformation between corresponding sets of points. Non-rigid registration, in particular, involves addressing challenges including various levels of deformation, noise, outliers, and data incompleteness. This paper introduces Robust-DefReg, a robust non-rigid point cloud registration method based on graph convolutional networks (GCNNs). Robust-DefReg is a coarse-to-fine registration approach within an end-to-end pipeline, leveraging the advantages of both coarse and fine methods. The method learns global features to find correspondences between source and target point clouds, to enable appropriate initial alignment, and subsequently fine registration. The simultaneous achievement of high accuracy and robustness across all challenges is reported less frequently in existing studies, making it a key objective of the Robust-DefReg method. The proposed method achieves high accuracy in large deformations while maintaining computational efficiency. This method possesses three primary attributes: high accuracy, robustness to different challenges, and computational efficiency. The experimental results show that the proposed Robust-DefReg holds significant potential as a foundational architecture for future investigations in non-rigid point cloud registration. The source code of Robust-DefReg is available.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 40 of its 96 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

40 of 96 references.

References · 40

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2015Spatial Transformer Networkscited by 1,423
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  7. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  8. 2017Learning from Synthetic Humanscited by 358
  9. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  10. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  11. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  12. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
28 more
  1. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  2. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  3. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  4. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 141
  5. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  6. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 128
  7. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  8. 2020Dual-Resolution Correspondence Networkscited by 90
  9. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  10. 2021A comprehensive survey on point cloud registrationcited by 84
  11. 2019DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Datacited by 76
  12. 2016Learning to Navigate the Energy Landscapecited by 62
  13. 20192D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloudcited by 62
  14. 2022A Survey of Non-Rigid 3D Registrationcited by 59
  15. 2022Non-rigid Point Cloud Registration with Neural Deformation Pyramidcited by 41
  16. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  17. 2015SceneNet: Understanding Real World Indoor Scenes With Synthetic Datacited by 29
  18. 2021ReAgent: Point Cloud Registration using Imitation and Reinforcement Learningcited by 23
  19. 2021PHASER: a Robust and Correspondence-free Global Pointcloud Registrationcited by 15
  20. 2018Learning to Reconstruct Texture-less Deformable Surfaces from a Single Viewcited by 11
  21. 2021Deep learning based geometric registration for medical images: How accurate can we get without visual features?cited by 10
  22. 2023Neural Intrinsic Embedding for Non-rigid Point Cloud Matchingcited by 9
  23. 2019DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxiescited by 8
  24. 2019Learning Deformable Point Set Registration with Regularized Dynamic Graph CNNs for Large Lung Motion in COPD Patientscited by 8
  25. 2020Unsupervised Learning of 3D Point Set Registrationcited by 7
  26. 2020DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registrationcited by 7
  27. 2019Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registrationcited by 6
  28. 2022A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registrationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformationcited by 2
  2. 2026DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registrationcited by 1
  3. 2025PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigationcited by 0
  4. 2026Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformationcited by 0