mlsanityData to 7 Oct 2026

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation

arXiv 2104.05328 ↗First posted 12 Apr 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel 2D-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module in our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of 12-15ms to register a pair of input point clouds as large as 250K. Extensive evaluation on (i) KITTI LiDAR odometry and (ii) ModelNet-40 datasets shows that our method outperforms prior state-of-the-art methods - e.g., on the KITTI data set, DCP-v2 by1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and other disturbances. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 78 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

35 of 78 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  9. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  10. 2017A simple neural network module for relational reasoningcited by 345
  11. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  12. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
23 more
  1. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  2. 2020Deep Global Registrationcited by 228
  3. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  4. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  5. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  6. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  7. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  8. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  9. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  10. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  11. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  12. 2019DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registrationcited by 77
  13. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 72
  14. 2019LO-Net: Deep Real-time Lidar Odometrycited by 59
  15. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  16. 2017Learning Compact Geometric Featurescited by 45
  17. 2018FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterizationcited by 43
  18. 2019Adaptive Hierarchical Down-Sampling for Point Cloud Classificationcited by 40
  19. 20193D Local Features for Direct Pairwise Registrationcited by 26
  20. 2020High-dimensional Convolutional Networks for Geometric Pattern Recognitioncited by 24
  21. 2019AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objectscited by 12
  22. 2020Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equationscited by 3
  23. 20193D point cloud registration with shape constraintcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 1; 2025: 0; 2026: 1.

8 papers.

  1. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  2. 2022Reliable Inlier Evaluation for Unsupervised Point Cloud Registrationcited by 19
  3. 2024Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extensioncited by 15
  4. 2023DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transportcited by 7
  5. 2023APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstructioncited by 3
  6. 2022TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Networkcited by 2
  7. 2023Overlap Bias Matching is Necessary for Point Cloud Registrationcited by 2
  8. 2026NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Drivingcited by 0