Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis (2403.11113v1)

Published 17 Mar 2024 in cs.CV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Crosspoint: Self-supervised cross-modal contrastive learning for 3d point cloud understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9902–9912, 2022.
  2. 3d semantic parsing of large-scale indoor spaces. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  3. Clusternet: Deep hierarchical cluster network with rigorously rotation-invariant representation for point cloud analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  4. Why discard if you can recycle?: A recycling max pooling module for 3d point cloud analysis. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 559–567, 2022.
  5. The devil is in the pose: Ambiguity-free 3d rotation-invariant learning via pose-aware convolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7472–7481, 2022.
  6. Vector neurons: A general framework for so(3)-equivariant networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 12200–12209, 2021.
  7. Condaformer: Disassembled transformer with local structure enhancement for 3d point cloud understanding. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  8. Learning so(3) equivariant representations with spherical cnns. In Proceedings of the European Conference on Computer Vision (ECCV), 2018.
  9. Se(3)-transformers: 3d roto-translation equivariant attention networks. In Advances in Neural Information Processing Systems, pages 1970–1981. Curran Associates, Inc., 2020.
  10. 3d semantic segmentation with submanifold sparse convolutional networks. CVPR, 2018.
  11. Pct: Point cloud transformer. Computational Visual Media, 7(2):187–199, 2021.
  12. Context-aware alignment and mutual masking for 3D-language pre-training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10984–10994, 2023.
  13. Learning from protein structure with geometric vector perceptrons. In International Conference on Learning Representations, 2021.
  14. Rotation-invariant local-to-global representation learning for 3d point cloud. In Advances in Neural Information Processing Systems, pages 8174–8185. Curran Associates, Inc., 2020.
  15. Escape from cells: Deep kd-networks for the recognition of 3d point cloud models. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017.
  16. A closer look at rotation-invariant deep point cloud analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16218–16227, 2021.
  17. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983, 2016.
  18. Equivariant point cloud analysis via learning orientations for message passing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18932–18941, 2022.
  19. Rethinking network design and local geometry in point cloud: A simple residual mlp framework. arXiv preprint arXiv:2202.07123, 2022.
  20. Voxnet: A 3d convolutional neural network for real-time object recognition. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 922–928. IEEE, 2015.
  21. A functional approach to rotation equivariant non-linearities for tensor field networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 13174–13183, 2021.
  22. Volumetric and multi-view cnns for object classification on 3d data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  23. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017a.
  24. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2017b.
  25. Spherical fractal convolutional neural networks for point cloud recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  26. E (n) equivariant graph neural networks. In International conference on machine learning, pages 9323–9332. PMLR, 2021.
  27. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In International Conference on Machine Learning, pages 9377–9388. PMLR, 2021.
  28. Multi-view convolutional neural networks for 3d shape recognition. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015.
  29. Svnet: Where so (3) equivariance meets binarization on point cloud representation. In International Conference on 3D Vision, 2022.
  30. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  31. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  32. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  33. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (TOG), 2019.
  34. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015a.
  35. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1912–1920, 2015b.
  36. Walk in the cloud: Learning curves for point clouds shape analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 915–924, 2021.
  37. Endowing deep 3d models with rotation invariance based on principal component analysis. In 2020 IEEE international conference on multimedia and expo (ICME), pages 1–6. IEEE, 2020.
  38. Sgmnet: Learning rotation-invariant point cloud representations via sorted gram matrix. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 10468–10477, 2021a.
  39. Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3173–3182, 2021b.
  40. 2dpass: 2d priors assisted semantic segmentation on lidar point clouds. In European Conference on Computer Vision, pages 677–695. Springer, 2022.
  41. Geometry and uncertainty-aware 3D point cloud class-incremental semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21759–21768, 2023.
  42. A scalable active framework for region annotation in 3d shape collections. ACM Transactions on Graphics (ToG), 35(6):1–12, 2016.
  43. Deep positional and relational feature learning for rotation-invariant point cloud analysis. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part X 16, pages 217–233. Springer, 2020.
  44. Parot: Patch-wise rotation-invariant network via feature disentanglement and pose restoration. In AAAI Conference on Artificial Intelligence, 2023.
  45. Learning rotation-invariant representations of point clouds using aligned edge convolutional neural networks. In 2020 International Conference on 3D Vision (3DV), pages 200–209. IEEE, 2020.
  46. Pointclip: Point cloud understanding by clip. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8552–8562, 2022.
  47. Rotation invariant convolutions for 3d point clouds deep learning. In International Conference on 3D Vision (3DV), 2019.
  48. Pointweb: Enhancing local neighborhood features for point cloud processing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  49. Point transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16259–16268, 2021.
  50. Adaptive graph convolution for point cloud analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4965–4974, 2021.
  51. Perception-aware multi-sensor fusion for 3d lidar semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16280–16290, 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now