mlsanityData to 7 Oct 2026

RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds

arXiv 2205.11028 ↗First posted 23 May 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow. However, these methods are limited by the fact that it is difficult to define a search window on point clouds because of the irregular data structure. In this paper, we avoid this irregularity by a simple yet effective method.We decompose the problem into two interlaced stages, where the 3D flows are optimized point-wisely at the first stage and then globally regularized in a recurrent network at the second stage. Therefore, the recurrent network only receives the regular point-wise information as the input. In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task. For 3D scene flow estimation, we make comparisons on the widely used FlyingThings3D and KITTIdatasets. For point cloud registration, we follow previous works and evaluate the data pairs with large pose and partially overlapping from ModelNet40. The results show that our method outperforms the previous method and achieves a new state-of-the-art performance on both 3D scene flow estimation and point cloud registration, which demonstrates the superiority of the proposed zero-order method on irregular point cloud data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

34 of 70 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
22 more
  1. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  2. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  3. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  4. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  5. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  6. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  7. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  8. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  9. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  10. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  11. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  12. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  13. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  14. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  15. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 100
  16. 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 96
  17. 2020FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimationcited by 71
  18. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
  19. 2019PCRNet: Point Cloud Registration Network using PointNet Encodingcited by 63
  20. 2020Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motioncited by 41
  21. 2019An Algorithm Unrolling Approach to Deep Image Deblurringcited by 14
  22. 2018Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registrationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  2. 2023GMSF: Global Matching Scene Flowcited by 14
  3. 2024RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 1
  4. 2024EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Supportcited by 0
  5. 2026SF3D-RGB: Scene Flow Estimation from Monocular Camera and Sparse LiDARcited by 0