Papers
Topics
Authors
Recent
Search
2000 character limit reached

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning

Published 5 Jan 2024 in cs.CV | (2401.02610v2)

Abstract: Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting local features through GCNs, while ignoring the relationship between point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between the voxelized point parts, which are treated as graph nodes. Motivated by the intuition that the contextual information between point parts lies in the pairwise adjacent relationship, which can be depicted by the hop distance of the graph quantitatively, we devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. In addition, we propose the Hop Graph Attention (HGA), which takes the learned hop distance as input for producing attention weights to allow edge features to contribute distinctively in aggregation. Eventually, the proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks. Comprehensive experiments on different backbones and tasks demonstrate that our self-supervised method achieves state-of-the-art performance. Our source code is available at: https://github.com/Jinec98/DHGCN.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Learning representations and generative models for 3d point clouds. In International conference on machine learning, 40–49. PMLR.
  2. 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, 9902–9912.
  3. Graph-based object classification for neuromorphic vision sensing. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 491–501.
  4. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012.
  5. Shape self-correction for unsupervised point cloud understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8382–8391.
  6. 4dcontrast: Contrastive learning with dynamic correspondences for 3d scene understanding. arXiv preprint arXiv:2112.02990.
  7. Chung, F. R. 1997. Spectral graph theory, volume 92. American Mathematical Soc.
  8. IterativePFN: True Iterative Point Cloud Filtering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13530–13539.
  9. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29.
  10. GraphTER: Unsupervised learning of graph transformation equivariant representations via auto-encoding node-wise transformations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7163–7172.
  11. Pct: Point cloud transformer. Computational Visual Media, 7(2): 187–199.
  12. View inter-prediction gan: Unsupervised representation learning for 3d shapes by learning global shape memories to support local view predictions. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 8376–8384.
  13. Multi-Angle Point Cloud-VAE: Unsupervised feature learning for 3D point clouds from multiple angles by joint self-reconstruction and half-to-half prediction. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 10441–10450. IEEE.
  14. Unsupervised multi-task feature learning on point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8160–8171.
  15. Spatio-temporal self-supervised representation learning for 3d point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6535–6545.
  16. Unsupervised contrastive learning with simple transformation for 3D point cloud data. The Visual Computer, 1–18.
  17. Masked autoencoders in 3d point cloud representation learning. IEEE Transactions on Multimedia.
  18. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  19. Large-scale point cloud semantic segmentation with superpoint graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4558–4567.
  20. Deepgcns: Making gcns go as deep as cnns. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  21. So-net: Self-organizing network for point cloud analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition, 9397–9406.
  22. Pointcnn: Convolution on x-transformed points. Advances in neural information processing systems, 31.
  23. Convolution in the cloud: Learning deformable kernels in 3d graph convolution networks for point cloud analysis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1800–1809.
  24. Rethinking network design and local geometry in point cloud: A simple residual mlp framework. arXiv preprint arXiv:2202.07123.
  25. Masked autoencoders for point cloud self-supervised learning. In European conference on computer vision, 604–621. Springer.
  26. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 652–660.
  27. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30.
  28. 3d graph neural networks for rgbd semantic segmentation. In Proceedings of the IEEE International Conference on Computer Vision, 5199–5208.
  29. Global-local bidirectional reasoning for unsupervised representation learning of 3d point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5376–5385.
  30. Self-supervised deep learning on point clouds by reconstructing space. Advances in Neural Information Processing Systems, 32.
  31. Point-gnn: Graph neural network for 3d object detection in a point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1711–1719.
  32. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision, 6411–6420.
  33. 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, 1588–1597.
  34. Attention is all you need. Advances in neural information processing systems, 30.
  35. Graph attention networks. arXiv preprint arXiv:1710.10903.
  36. Unsupervised point cloud pre-training via occlusion completion. In Proceedings of the IEEE/CVF international conference on computer vision, 9782–9792.
  37. Graph attention convolution for point cloud semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 10296–10305.
  38. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5): 1–12.
  39. Self-supervised learning on graphs: Contrastive, generative, or predictive. IEEE Transactions on Knowledge and Data Engineering.
  40. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1912–1920.
  41. Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. In European conference on computer vision, 574–591. Springer.
  42. Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3173–3182.
  43. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 206–215.
  44. A scalable active framework for region annotation in 3d shape collections. ACM Transactions on Graphics (ToG), 35(6): 1–12.
  45. Graph classification via discriminative edge feature learning. Pattern Recognition, 143: 109799.
  46. Point-bert: Pre-training 3d point cloud transformers with masked point modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 19313–19322.
  47. Pointfilter: Point cloud filtering via encoder-decoder modeling. IEEE Transactions on Visualization and Computer Graphics, 27(3): 2015–2027.
  48. 3D point capsule networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1009–1018.
  49. Adaptive graph convolution for point cloud analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4965–4974.
Citations (4)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up