mlsanityData to 7 Oct 2026

3D Point Cloud Registration with Learning-based Matching Algorithm

arXiv 2202.02149 ↗First posted 4 Feb 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a novel differential matching algorithm for 3D point cloud registration. Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the jointly-trained feature extractor. We focused on edge-wise feature-forwarding architectures, which are memory-consuming but can avoid the over-smoothing effect that GNNs suffer. We improve its memory efficiency to scale it for point cloud registration while investigating the best way of connecting it to the feature extractor. Experimental results show our matching module's significant impact on performance improvement in rigid/non-rigid and whole/partial point cloud registration datasets with multiple contemporary feature extractors. For example, our module boosted the current SOTA method, RoITr, by +5.4%, and +7.2% in the NFMR metric and +6.1% and +8.5% in the IR metric on the 4DMatch and 4DLoMatch datasets, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

28 of 51 references.

References · 28

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2017Deep Setscited by 1,394
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  9. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  10. 2017Learning from Synthetic Humanscited by 358
  11. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  12. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
16 more
  1. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  2. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  3. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  4. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  5. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  6. 2018Neighbourhood Consensus Networkscited by 173
  7. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  8. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  9. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  10. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  11. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  12. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  13. 2019PCRNet: Point Cloud Registration Network using PointNet Encodingcited by 63
  14. 2020CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Cloudscited by 47
  15. 2020Human Motion Transfer with 3D Constraints and Detail Enhancementcited by 14
  16. 20183D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Artcited by 7

Built on by

Not cited yet.