mlsanityData to 7 Oct 2026

Rethinking Rotation Invariance with Point Cloud Registration

arXiv 2301.00149 ↗First posted 31 Dec 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotation-invariant feature descriptors or learning canonical spaces where objects are semantically aligned. Examinations of learning frameworks for invariance have seldom been looked into. In this work, we review rotation invariance in terms of point cloud registration and propose an effective framework for rotation invariance learning via three sequential stages, namely rotation-invariant shape encoding, aligned feature integration, and deep feature registration. We first encode shape descriptors constructed with respect to reference frames defined over different scales, e.g., local patches and global topology, to generate rotation-invariant latent shape codes. Within the integration stage, we propose Aligned Integration Transformer to produce a discriminative feature representation by integrating point-wise self- and cross-relations established within the shape codes. Meanwhile, we adopt rigid transformations between reference frames to align the shape codes for feature consistency across different scales. Finally, the deep integrated feature is registered to both rotation-invariant shape codes to maximize feature similarities, such that rotation invariance of the integrated feature is preserved and shared semantic information is implicitly extracted from shape codes. Experimental results on 3D shape classification, part segmentation, and retrieval tasks prove the feasibility of our work. Our project page is released at: https://rotation3d.github.io/.

Key facts. Cited by 5 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 31 Dec 2022.

Builds on

42 of 58 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2020Point Transformercited by 1,462
  12. 2015Spatial Transformer Networkscited by 1,423
30 more
  1. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  2. 2020PCT: Point cloud transformercited by 730
  3. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  4. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  5. 2018Spherical CNNscited by 452
  6. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  7. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  9. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  10. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  11. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  12. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  13. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  14. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  15. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  16. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  17. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  18. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  19. 2020Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learningcited by 68
  20. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  21. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  22. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  23. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  24. 2020Global Context Aware Convolutions for 3D Point Cloud Understandingcited by 26
  25. 2020Learning to Orient Surfaces by Self-supervised Spherical CNNscited by 26
  26. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  27. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  28. 2022The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolutioncited by 18
  29. 2021Robust Partial-to-Partial Point Cloud Registration in a Full Rangecited by 8
  30. 2020Rotation-Invariant Point Convolution With Multiple Equivariant Alignmentscited by 7

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  2. 2024Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Trainingcited by 1
  3. 2025HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysiscited by 1
  4. 2024Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Modulecited by 0
  5. 2025Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoderscited by 0