mlsanityData to 7 Oct 2026

General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

arXiv 2302.09907 ↗First posted 20 Feb 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Compared to 2D images, 3D point clouds are much more sensitive to rotations. We expect the point features describing certain patterns to keep invariant to the rotation transformation. There are many recent SOTA works dedicated to rotation-invariant learning for 3D point clouds. However, current rotation-invariant methods lack generalizability on the point clouds in the open scenes due to the reliance on the global distribution, ie the global scene and backgrounds. Considering that the output activation is a function of the pattern and its orientation, we need to eliminate the effect of the orientation.In this paper, inspired by the idea that the network weights can be considered a set of points distributed in the same 3D space as the input points, we propose Weight-Feature Alignment (WFA) to construct a local Invariant Reference Frame (IRF) via aligning the features with the principal axes of the network weights. Our WFA algorithm provides a general solution for the point clouds of all scenes. WFA ensures the model achieves the target that the response activity is a necessary and sufficient condition of the pattern matching degree. Practically, we perform experiments on the point clouds of both single objects and open large-range scenes. The results suggest that our method almost bridges the gap between rotation invariance learning and normal methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

42 of 58 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Point Transformercited by 1,462
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 2016Group Equivariant Convolutional Networkscited by 1,154
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2020PCT: Point cloud transformercited by 730
30 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  2. 2018Spherical CNNscited by 452
  3. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  4. 2016Steerable CNNscited by 298
  5. 2021Voxel Transformer for 3D Object Detectioncited by 247
  6. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  7. 2017Submanifold Sparse Convolutional Networkscited by 223
  8. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  9. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  10. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  11. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  12. 2021Fast Point Transformercited by 103
  13. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  14. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  15. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  16. 2018CubeNet: Equivariance to 3D Rotation and Translationcited by 59
  17. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  18. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  19. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  20. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  21. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  22. 20193D-Rotation-Equivariant Quaternion Neural Networkscited by 30
  23. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  24. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  25. 2020Learning to Orient Surfaces by Self-supervised Spherical CNNscited by 26
  26. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  27. 2019Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysiscited by 17
  28. 2018Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolutioncited by 16
  29. 2020Triangle-Net: Towards Robustness in Point Cloud Learningcited by 13
  30. 2021Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networkscited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 20234D Panoptic Segmentation as Invariant and Equivariant Field Predictioncited by 19
  2. 2024RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learningcited by 15