mlsanityData to 7 Oct 2026

Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis

arXiv 2403.11113 ↗First posted 17 Mar 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Rotation invariance is an important requirement for point shape analysis. To achieve this, current state-of-the-art methods attempt to construct the local rotation-invariant representation through learning or defining the local reference frame (LRF). Although efficient, these LRF-based methods suffer from perturbation of local geometric relations, resulting in suboptimal local rotation invariance. To alleviate this issue, we propose a Local-consistent Transformation (LocoTrans) learning strategy. Specifically, we first construct the local-consistent reference frame (LCRF) by considering the symmetry of the two axes in LRF. In comparison with previous LRFs, our LCRF is able to preserve local geometric relationships better through performing local-consistent transformation. However, as the consistency only exists in local regions, the relative pose information is still lost in the intermediate layers of the network. We mitigate such a relative pose issue by developing a relative pose recovery (RPR) module. RPR aims to restore the relative pose between adjacent transformed patches. Equipped with LCRF and RPR, our LocoTrans is capable of learning local-consistent transformation and preserving local geometry, which benefits rotation invariance learning. Competitive performance under arbitrary rotations on both shape classification and part segmentation tasks and ablations can demonstrate the effectiveness of our method. Code will be available publicly at https://github.com/wdttt/LocoTrans.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 17 Mar 2024.

Builds on

36 of 51 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  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. 2020Point Transformercited by 1,462
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 2021E(n) Equivariant Graph Neural Networkscited by 951
  8. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  9. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  10. 2020PCT: Point cloud transformercited by 730
  11. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  12. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
24 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  4. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  5. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  6. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  7. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  8. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  9. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  10. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  11. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  12. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  13. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  14. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  15. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  16. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  17. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  18. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  19. 2022The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolutioncited by 18
  20. 2019Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysiscited by 17
  21. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  22. 2021Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networkscited by 12
  23. 2022SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representationcited by 10
  24. 2023PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restorationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7
  2. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  3. 2026FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Castingcited by 3
  4. 2024Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Trainingcited by 1
  5. 2024Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Modulecited by 0
  6. 2026RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrievalcited by 0