mlsanityData to 7 Oct 2026

A Rotation-Invariant Framework for Deep Point Cloud Analysis

arXiv 2003.07238 ↗First posted 16 Mar 2020cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this paper, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotation-invariant representations, we further introduce a region relation convolution to encode local and non-local information. We evaluate our method on multiple point cloud analysis tasks, including shape classification, part segmentation, and shape retrieval. Experimental results show that our method achieves consistent, and also the best performance, on inputs at arbitrary orientations, compared with the state-of-the-arts.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 18; 2023: 12; 2024: 15; 2025: 4; 2026: 4.

62 papers.

Sort:

By area:

  1. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  2. 2022Equivariance with Learned Canonicalization Functionscited by 106
  3. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  4. 20213D Question Answeringcited by 41
  5. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  6. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31
  7. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  8. 2022GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Networkcited by 22
  9. 2022Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spacescited by 20
  10. 2022The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolutioncited by 18
  11. 2022VectorAdam for Rotation Equivariant Geometry Optimizationcited by 17
  12. 2021Robustness Certification for Point Cloud Modelscited by 16
38 more
  1. 2021PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Featurescited by 15
  2. 2024RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentationcited by 15
  3. 2024Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passingcited by 13
  4. 2022ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotationcited by 12
  5. 2022A Simple and Universal Rotation Equivariant Point-cloud Networkcited by 11
  6. 2022SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representationcited by 10
  7. 2022LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsamplingcited by 8
  8. 2023Learning Harmonic Molecular Representations on Riemannian Manifoldcited by 8
  9. 2023PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restorationcited by 7
  10. 2023Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebrascited by 6
  11. 2021Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registrationcited by 5
  12. 2021RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Networkcited by 5
  13. 2022Rethinking Rotation Invariance with Point Cloud Registrationcited by 5
  14. 2024An intuitive multi-frequency feature representation for SO(3)-equivariant networkscited by 5
  15. 2024RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentationcited by 5
  16. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  17. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  18. 2025ShapeEmbed: a self-supervised learning framework for 2D contour quantificationcited by 4
  19. 2023S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classificationcited by 3
  20. 2023GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentationcited by 3
  21. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  22. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  23. 2025CS-Net:Contribution-based Sampling Network for Point Cloud Simplificationcited by 3
  24. 2026FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Castingcited by 3
  25. 2022TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysiscited by 2
  26. 2023PointSmile: Point Self-supervised Learning via Curriculum Mutual Informationcited by 2
  27. 2023General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignmentcited by 2
  28. 2023Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillationcited by 2
  29. 2024A general framework for rotation invariant point cloud analysiscited by 2
  30. 2024Efficient and Generic Point Model for Lossless Point Cloud Attribute Compressioncited by 2
  31. 2024VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understandingcited by 2
  32. 2021Angle Based Feature Learning in GNN for 3D Object Detection using Point Cloudcited by 1
  33. 2021Integrating Sensing and Communication in Cellular Networks via NR Sidelinkcited by 1
  34. 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Treescited by 1
  35. 2022SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancementcited by 1
  36. 2023Cloud-RAIN: Point Cloud Analysis with Reflectional Invariancecited by 1
  37. 2023Rotation-Invariant Completion Networkcited by 1
  38. 2024TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Trainingcited by 1

50 most cited of 62 All 62 (JSON)