mlsanityData to 14 Oct 2026

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

arXiv 2111.14582 ↗First posted 29 Nov 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject the outliers, whose robustness and efficiency degrade notably when the number of instances and outliers increase. We propose to directly group the set of noisy correspondences into different clusters based on a distance invariance matrix. The instances and outliers are automatically identified through clustering. Our method is robust and fast. We evaluated our method on both synthetic and real-world datasets. The results show that our approach can correctly register up to 20 instances with an F1 score of 90.46% in the presence of 70% outliers, which performs significantly better and at least 10x faster than existing methods

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 32 of its 57 references that are in the map. First posted on arXiv 29 Nov 2021.

Builds on

32 of 57 references.

References · 32

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  5. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  6. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  7. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  8. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  9. 2020Deep Global Registrationcited by 229
  10. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 182
  11. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  12. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
20 more
  1. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  2. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  3. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  4. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  5. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  6. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  7. 2017Graph-Cut RANSACcited by 133
  8. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  9. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 109
  10. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  11. 2017Guaranteed Outlier Removal for Point Cloud Registration with Correspondencescited by 62
  12. 2020SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scanscited by 44
  13. 2019Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithmcited by 43
  14. 2019End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scanscited by 40
  15. 2020ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariantscited by 38
  16. 2020CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensuscited by 30
  17. 2019A Practical Maximum Clique Algorithm for Matching with Pairwise Constraintscited by 20
  18. 2017Multi-Class Model Fitting by Energy Minimization and Mode-Seekingcited by 19
  19. 2019A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matchingcited by 10
  20. 2017In search of inliers: 3d correspondence by local and global votingcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 4; 2025: 1.

7 papers.

  1. 2024Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenescited by 7
  2. 2022PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registrationcited by 6
  3. 2024PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformercited by 6
  4. 2024Instance by Instance: An Iterative Framework for Multi-instance 3D Registrationcited by 2
  5. 20243D Registration in 30 Years: A Surveycited by 2
  6. 2023A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptorscited by 0
  7. 2025MRG: A Multi-Robot Manufacturing Digital Scene Generation Method Using Multi-Instance Point Cloud Registrationcited by 0