mlsanityData to 7 Oct 2026

Deep Global Registration

arXiv 2004.11540 ↗First posted 24 Apr 2020cs.CV cs.CG cs.LGcited by 228

Not on the map. Why?

Abstract (arXiv)

We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.

Key facts. Cited by 228 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 50; 2022: 46; 2023: 46; 2024: 39; 2025: 30; 2026: 17.

228 papers.

Sort:

By area:

  1. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  2. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  3. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  4. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  5. 2021A comprehensive survey on point cloud registrationcited by 84
  6. 20233D Registration with Maximal Cliquescited by 83
  7. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 83
  8. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  9. 2021LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAMcited by 67
  10. 2021ROCA: Robust CAD Model Retrieval and Alignment from a Single Imagecited by 66
  11. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  12. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
38 more
  1. 2023SiLK -- Simple Learned Keypointscited by 54
  2. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  3. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 47
  4. 2024Graspness Discovery in Clutters for Fast and Accurate Grasp Detectioncited by 47
  5. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  6. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  7. 2022Non-rigid Point Cloud Registration with Neural Deformation Pyramidcited by 41
  8. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  9. 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 40
  10. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
  11. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  12. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
  13. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  14. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  15. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 32
  16. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  17. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  18. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  19. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 28
  20. 2021Bootstrap Your Own Correspondencescited by 27
  21. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  22. 2025FG2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matchingcited by 27
  23. 2021Self-supervised Geometric Perceptioncited by 26
  24. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  25. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  26. 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registrationcited by 26
  27. 2021Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representationscited by 24
  28. 2021Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registrationcited by 24
  29. 2021ReAgent: Point Cloud Registration using Imitation and Reinforcement Learningcited by 23
  30. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  31. 2021Fast and Robust Registration of Partially Overlapping Point Cloudscited by 22
  32. 2022iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Trackingcited by 22
  33. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20
  34. 2022Reliable Inlier Evaluation for Unsupervised Point Cloud Registrationcited by 19
  35. 2022PeRFception: Perception using Radiance Fieldscited by 19
  36. 2022ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairscited by 17
  37. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 17
  38. 2024FastMAC: Stochastic Spectral Sampling of Correspondence Graphcited by 16

50 most cited of 228 All 228 (JSON)