mlsanityData to 14 Oct 2026

Geometric Transformer for Fast and Robust Point Cloud Registration

arXiv 2202.06688 ↗First posted 14 Feb 2022cs.CVcited by 202

Not on the map. Why?

Abstract (arXiv)

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in registration. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Our method improves the inlier ratio by 17~30 percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark. Our code and models are available at https://github.com/qinzheng93/GeoTransformer.

Key facts. Cited by 202 papers in the map (data through 14 Oct 2026). Builds on 38 of its 45 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

38 of 45 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2018Group Normalizationcited by 1,524
  7. 2020Point Transformercited by 1,470
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  10. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  11. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  12. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
26 more
  1. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  2. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  3. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  4. 2020Deep Global Registrationcited by 229
  5. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  6. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 182
  7. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  8. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
  9. 2018Neighbourhood Consensus Networkscited by 174
  10. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  11. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  12. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  13. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  14. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 142
  15. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  16. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  17. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 129
  18. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 109
  19. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 103
  20. 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 97
  21. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  22. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  23. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  24. 2021OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registrationcited by 51
  25. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 48
  26. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 21; 2023: 54; 2024: 46; 2025: 44; 2026: 37.

202 papers.

Sort:

By area:

  1. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  2. 20233D Registration with Maximal Cliquescited by 84
  3. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 84
  4. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  5. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 69
  6. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  7. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  8. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  9. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  10. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  11. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  12. 2023FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimatorscited by 31
38 more
  1. 2022Generalized Differentiable RANSACcited by 30
  2. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  3. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 29
  4. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  5. 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registrationcited by 27
  6. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  7. 2022RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registrationcited by 25
  8. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  9. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 19
  10. 2024GaussReg: Fast 3D Registration with Gaussian Splattingcited by 19
  11. 2024MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Mapscited by 18
  12. 2023DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matchingcited by 17
  13. 2024FastMAC: Stochastic Spectral Sampling of Correspondence Graphcited by 16
  14. 2022ObjectMatch: Robust Registration using Canonical Object Correspondencescited by 15
  15. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 15
  16. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  17. 2023Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAMcited by 15
  18. 2023Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environmentscited by 15
  19. 2024Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extensioncited by 15
  20. 2024Crystalformer: Infinitely Connected Attention for Periodic Structure Encodingcited by 15
  21. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 15
  22. 2022A Cooperative Perception System Robust to Localization Errorscited by 14
  23. 2022DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimizationcited by 14
  24. 2023GMSF: Global Matching Scene Flowcited by 14
  25. 2023PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registrationcited by 14
  26. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  27. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  28. 2023PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometrycited by 13
  29. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  30. 2025TurboReg: TurboClique for Robust and Efficient Point Cloud Registrationcited by 13
  31. 2023Rearrangement Planning for General Part Assemblycited by 12
  32. 2023Density-invariant Features for Distant Point Cloud Registrationcited by 12
  33. 2023CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registrationcited by 12
  34. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  35. 2025IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environmentscited by 11
  36. 2022Overlap-guided Gaussian Mixture Models for Point Cloud Registrationcited by 10
  37. 2024SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Taskscited by 10
  38. 2025ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Planscited by 10

50 most cited of 202 All 202 (JSON)