mlsanityData to 7 Oct 2026

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

arXiv 2102.12093 ↗First posted 24 Feb 2021cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Point-wise Rotation Invariant Network, focusing on rotation invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point. In addition, we extend PRIN to a sparse version called SPRIN, which directly operates on sparse point clouds. Both PRIN and SPRIN can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. Results show that, on the dataset with randomly rotated point clouds, SPRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide thorough theoretical proof and analysis for point-wise rotation invariance achieved by our methods. Our code is available on https://github.com/qq456cvb/SPRIN.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

37 of 55 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2017Deep Setscited by 1,394
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2018Computational Optimal Transportcited by 765
  8. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  9. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  10. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  11. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
25 more
  1. 2018Spherical CNNscited by 452
  2. 2016Steerable CNNscited by 298
  3. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  4. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  5. 2017Submanifold Sparse Convolutional Networkscited by 223
  6. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  7. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  8. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  9. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  10. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  11. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  12. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  13. 2015Rotation-invariant convolutional neural networks for galaxy morphology predictioncited by 83
  14. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  15. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  16. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  17. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  18. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  19. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  20. 2017Learning Compact Geometric Featurescited by 45
  21. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  22. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  23. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  24. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  25. 2018Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolutioncited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 6; 2025: 2; 2026: 1.

15 papers.

Sort:

  1. 2022CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wildcited by 28
  2. 2022USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulationcited by 27
  3. 2024General Place Recognition Survey: Towards Real-World Autonomycited by 23
  4. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  5. 2024RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learningcited by 15
  6. 2021RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Networkcited by 5
  7. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  8. 2023CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Framecited by 4
  9. 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Featurescited by 4
  10. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  11. 2024SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapescited by 1
  12. 2023Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariancecited by 0
3 more
  1. 2024DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perceptioncited by 0
  2. 2024Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillationcited by 0
  3. 2026Leveraging a Statistical Shape Model for Efficient Generation of Annotated Training Data: A Case Study on Liver Landmarks Segmentationcited by 0