mlsanityData to 14 Oct 2026

Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance

arXiv 2305.07814 ↗First posted 13 May 2023cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The networks for point cloud tasks are expected to be invariant when the point clouds are affinely transformed such as rotation and reflection. So far, relative to the rotational invariance that has been attracting major research attention in the past years, the reflection invariance is little addressed. Notwithstanding, reflection symmetry can find itself in very common and important scenarios, e.g., static reflection symmetry of structured streets, dynamic reflection symmetry from bidirectional motion of moving objects (such as pedestrians), and left- and right-hand traffic practices in different countries. To the best of our knowledge, unfortunately, no reflection-invariant network has been reported in point cloud analysis till now. To fill this gap, we propose a framework by using quadratic neurons and PCA canonical representation, referred to as Cloud-RAIN, to endow point underlineCloud models with underlineReflectionunderlineAl underlineINvariance. We prove a theorem to explain why Cloud-RAIN can enjoy reflection symmetry. Furthermore, extensive experiments also corroborate the reflection property of the proposed Cloud-RAIN and show that Cloud-RAIN is superior to data augmentation. Our code is available at https://github.com/YimingCuiCuiCui/Cloud-RAIN.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 13 May 2023.

Builds on

44 of 66 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020Point Transformercited by 1,470
  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 1,205
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  10. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  12. 2016Error bounds for approximations with deep ReLU networkscited by 574
32 more
  1. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  2. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  3. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  4. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  5. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  6. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  7. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  8. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  9. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  10. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  11. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  12. 2021Fast Point Transformercited by 104
  13. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  14. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  15. 2020Deep Polynomial Neural Networkscited by 63
  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. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  19. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  20. 2021Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEscited by 43
  21. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  22. 2017Non-linear Convolution Filters for CNN-based Learningcited by 38
  23. 2019Quadratic Autoencoder (Q-AE) for Low-dose CT Denoisingcited by 35
  24. 2021Tree Decomposed Graph Neural Networkcited by 35
  25. 2019Geometry Sharing Network for 3D Point Cloud Classification and Segmentationcited by 33
  26. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  27. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  28. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  29. 2022QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Explorationcited by 21
  30. 2019Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysiscited by 17
  31. 2017A New Type of Neurons for Machine Learningcited by 16
  32. 2023One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networkscited by 6

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Seeing through Unclear Glass: Occlusion Removal with One Shotcited by 1