mlsanityData to 7 Oct 2026

Overlap-guided Gaussian Mixture Models for Point Cloud Registration

arXiv 2210.09836 ↗First posted 17 Oct 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations. However, registering point cloud pairs in the case of partial overlap is still a challenge. This paper proposes a novel overlap-guided probabilistic registration approach that computes the optimal transformation from matched Gaussian Mixture Model (GMM) parameters. We reformulate the registration problem as the problem of aligning two Gaussian mixtures such that a statistical discrepancy measure between the two corresponding mixtures is minimized. We introduce a Transformer-based detection module to detect overlapping regions, and represent the input point clouds using GMMs by guiding their alignment through overlap scores computed by this detection module. Experiments show that our method achieves superior registration accuracy and efficiency than state-of-the-art methods when handling point clouds with partial overlap and different densities on synthetic and real-world datasets. https://github.com/gfmei/ogmm

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

32 of 54 references.

References · 32

  1. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  3. 2020Point Transformercited by 1,462
  4. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  5. 2018Computational Optimal Transportcited by 765
  6. 2020PCT: Point cloud transformercited by 730
  7. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  8. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  9. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  10. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  11. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  12. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
20 more
  1. 2020Deep Global Registrationcited by 228
  2. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  3. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  4. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  5. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 108
  6. 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 96
  7. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  8. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  9. 2021OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registrationcited by 50
  10. 2018FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterizationcited by 43
  11. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  12. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 41
  13. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  14. 2016Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximizationcited by 19
  15. 2022Reliable Inlier Evaluation for Unsupervised Point Cloud Registrationcited by 19
  16. 2015An Adaptive Data Representation for Robust Point-Set Registration and Mergingcited by 11
  17. 2018Density Adaptive Point Set Registrationcited by 11
  18. 2021Loop closure detection using local 3D deep descriptorscited by 8
  19. 2020Wasserstein k-means with sparse simplex projectioncited by 6
  20. 2020Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Explorationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 4; 2026: 1.

10 papers.

  1. 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registrationcited by 26
  2. 2023Novel Class Discovery for 3D Point Cloud Semantic Segmentationcited by 21
  3. 2023ZeroReg: Zero-Shot Point Cloud Registration with Foundation Modelscited by 6
  4. 2025RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learningcited by 5
  5. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  6. 2025Fully-Geometric Cross-Attention for Point Cloud Registrationcited by 3
  7. 20243D Registration in 30 Years: A Surveycited by 2
  8. 2025LPRnet: A self-supervised registration network for LiDAR and photogrammetric point cloudscited by 1
  9. 2025KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Searchcited by 0
  10. 2026TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisationcited by 0