Hypergraph Position Attention Convolution Networks for 3D Point Cloud Segmentation
Source abstract
Abstract
Point cloud segmentation, as the basis for 3D scene understanding and analysis, has made significant progress in recent years. Graph-based modeling and learning methods have played an important role in point cloud segmentation. However, due to the inherent complexity of point cloud data, it is difficult to capture higher-order and complex features of 3D data using graph learning methods. In addition, how to quickly and efficiently extract important features from point clouds also poses a great challenge to the current research. To address these challenges, we propose a new framework, called hypergraph position attention convolution networks (HGPAT), for point cloud segmentation. Firstly, we use hypergraph to model the higher-order relationships among point clouds. Secondly, in order to effectively learn the feature information of point cloud data, a hyperedge position attention convolution module is proposed, which utilizes the hyperedge–hyperedge propagation pattern to extract and aggregate more important features. Finally, we design a ResNet-like module to reduce the computational complexity of the network and improve its efficiency. We have conducted point cloud segmentation experiments on the ShapeNet Part and S3IDS datasets, and the experimental results demonstrate the effectiveness of the proposed method compared with the state-of-the-art ones.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Shape Modeling and Analysis · Remote Sensing and LiDAR Applications · 3D Surveying and Cultural Heritage
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Information Engineering/School of Integrated Circuits, Guangxi Normal University, Guilin 541004, China
College of Physics and Technology, Guangxi Normal University, Guilin 541004, China
School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China
College of Computer Science and Engineering, Guangxi Normal University, Guilin 541004, China
Funding
Guangxi Science and Technology Program · National Natural Science Foundation of China · Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education
References (54)
Show source-provided references
1. Deep learning for 3d point clouds: A survey10.1109/TPAMI.2020.3005434 ↗
2. Cao, Y., Teruggi, S., Fassi, F., and Scaioni, M. (2022, January 20–24). A Comprehensive Understanding of Machine Learning and Deep Learning Methods for 3D Architectural Cultural Heritage Point Cloud Semantic Segmentation. Proceedings of the Italian Conference on Geomatics and Geospatial Technologies, Genova, Italy.10.1007/978-3-031-17439-1_24 ↗
3. A method for creating interactive, user-resembling avatars10.7717/peerj-cs.128 ↗
4. Qi, C., Su, H., Mo, K., and Guibas, L.J. (2017, January 21–26). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.
5. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst., 30.
6. Dynamic graph cnn for learning on point clouds
7. Point clouds learning with attention-based graph convolution networks10.1016/j.neucom.2020.03.086 ↗
8. Wang, L., Huang, Y., Hou, Y., Shenman, Z., and Shan, J. (2019, January 15–20). Graph Attention Convolution for Point Cloud Semantic Segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01054 ↗
9. Liang, Z., Yang, M., Deng, L., Wang, C., and Wang, B. (2019, January 20–24). Hierarchical Depthwise Graph Convolutional Neural Network for 3D Semantic Segmentation of Point Clouds. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8794052 ↗
10. Networks beyond pairwise interactions: Structure and dynamics10.1016/j.physrep.2020.05.004 ↗
11. Bretto, A. (2013). An Introduction. Mathematical Engineering, Springer.10.1007/978-3-319-00080-0 ↗
12. Hypergraph Spectral Analysis and Processing in 3D Point Cloud10.1109/TIP.2020.3042088 ↗
13. Hypergraph Spectral Clustering for Point Cloud Segmentation10.1109/LSP.2020.3023587 ↗
14. Hypergraph Representation for Detecting 3D Objects from Noisy Point Clouds
15. An Efficient Hypergraph Approach to Robust Point Cloud Resampling10.1109/TIP.2022.3149225 ↗
16. 3-D object retrieval and recognition with hypergraph analysis10.1109/TIP.2012.2199502 ↗
17. Hypergraph Neural Network for Skeleton-Based Action Recognition10.1109/TIP.2021.3051495 ↗
18. Huang, Y., and Lu, H. (2016, January 12–16). Deep learning driven hypergraph representation for image-based emotion recognition. Proceedings of the 18th ACM International Conference on Multimodal Interaction, Tokyo, Japan.10.1145/2993148.2993185 ↗
19. Wang, J., Ding, K., Zhu, Z., and Caverlee, J. (May, January 29). Session-based Recommendation with Hypergraph Attention Networks. Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), Virtual Event.10.1137/1.9781611976700.10 ↗
20. Feng, Y., You, H., Zhang, Z., Ji, R., and Gao, Y. (2018, January 2–7). Hypergraph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.
21. Chen, C., Cheng, Z., Li, Z., and Wang, M. (2020, January 29). Hypergraph Attention Networks. Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Guangzhou, China.10.1109/TrustCom50675.2020.00215 ↗
22. Jiang, J., Wei, Y., Feng, Y., Cao, J., and Gao, Y. (2019, January 10–16). Dynamic Hypergraph Neural Networks. Proceedings of the IJCAI, Macao, China.10.24963/ijcai.2019/366 ↗
23. Zhu, J., Zhao, X., Hu, H., and Gao, Y. (2019, January 8–12). Emotion Recognition from Physiological Signals using Multi-Hypergraph Neural Networks. Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China.10.1109/ICME.2019.00111 ↗
24. Webber, B., Cohn, T., He, Y., and Liu, Y. (2020, January 16–20). Be More with Less: Hypergraph Attention Networks for Inductive Text Classification. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.
25. Hypergcn: A new method for training graph convolutional networks on hypergraphs
26. Hypergraph convolution and hypergraph attention10.1016/j.patcog.2020.107637 ↗
27. Liu, S., Lv, P., Zhang, Y., Fu, J., Cheng, J., Li, W., Zhou, B., and Xu, M. (2020, January 11–17). Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation. Proceedings of the International Joint Conference on Artificial Intelligence, Yokohama, Japan.10.24963/ijcai.2020/109 ↗
28. Maturana, D., and Scherer, S. (October, January 28). Voxnet: A 3d convolutional neural network for real-time object recognition. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.10.1109/IROS.2015.7353481 ↗
29. Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7–13). Multi-view convolutional neural networks for 3d shape recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.114 ↗
30. Wu, B., Zhou, X., Zhao, S., Yue, X., and Keutzer, K. (2019, January 20–24). Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8793495 ↗
31. Jung, T.W., Jeong, C.S., Kim, I.S., Yu, M.S., Kwon, S.C., and Jung, K.D. (2022). Graph Convolutional Network for 3D Object Pose Estimation in a Point Cloud. Sensors, 22.10.3390/s22218166 ↗
32. Bandyopadhyay, S., Das, K., and Murty, M.N. (2020). Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs. arXiv.
33. Kim, E.S., Kang, W.Y., On, K.W., Heo, Y.J., and Zhang, B.T. (2020, January 13–19). Hypergraph Attention Networks for Multimodal Learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01459 ↗
34. Liu, J., Xue, Z., and Li, A. (2022, January 26–28). Scientific Paper Classification Based on Graph Neural Network with Hypergraph Self-attention Mechanism. Proceedings of the 2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS), Chengdu, China.10.1109/CCIS57298.2022.10016409 ↗
35. Temporal Hypergraph Attention Network for Silicon Content Prediction in Blast Furnace10.1109/TIM.2022.3219307 ↗
36. Temporal-relational hypergraph tri-attention networks for stock trend prediction10.1016/j.patcog.2023.109759 ↗
37. Zhou, D., Huang, J., and Schölkopf, B. (2006). Learning with hypergraphs: Clustering, classification, and embedding. Adv. Neural Inf. Process. Syst., 19.10.7551/mitpress/7503.003.0205 ↗
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
40. Armeni, I., Sener, O., Zamir, A.R., Jiang, H., Brilakis, I., Fischer, M., and Savarese, S. (2016, January 27–30). 3d semantic parsing of large-scale indoor spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.170 ↗
41. A scalable active framework for region annotation in 3d shape collections10.1145/2980179.2980238 ↗
42. Xu, M., Ding, R., Zhao, H., and Qi, X. (2021, January 20–25). Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00319 ↗
43. Jing, W., Zhang, W., Li, L., Di, D., Chen, G., and Wang, J. (2022). AGNet: An attention-based graph network for point cloud classification and segmentation. Remote Sens., 14.10.3390/rs14041036 ↗
44. Lei, H., Akhtar, N., and Mian, A. (2020, January 13–19). Seggcn: Efficient 3d point cloud segmentation with fuzzy spherical kernel. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01163 ↗
45. Zhao, H., Jiang, L., Fu, C.W., and Jia, J. (2019, January 15–20). Pointweb: Enhancing local neighborhood features for point cloud processing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00571 ↗
46. Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L.J. (2019, January 15–20). Kpconv: Flexible and deformable convolution for point clouds. Proceedings of the IEEE/CVF International Conference on Computer Vision, Long Beach, CA, USA.10.1109/ICCV.2019.00651 ↗
47. GAPointNet: Graph attention based point neural network for exploiting local feature of point cloud10.1016/j.neucom.2021.01.095 ↗
48. Wang, Z., Wang, Y., An, L., Liu, J., and Liu, H. (2022). Local transformer network on 3d point cloud semantic segmentation. Information, 13.10.3390/info13040198 ↗
49. He, L., She, J., Zhao, Q., Wen, X., and Guan, Y. (2023). Boundary–Inner Disentanglement Enhanced Learning for Point Cloud Semantic Segmentation. Appl. Sci., 13.10.3390/app13064053 ↗
50. Robert, D., Raguet, H., and Landrieu, L. (2024). Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering. arXiv.10.1109/3DV62453.2024.00135 ↗
51. Wu, W., Qi, Z., and Fuxin, L. (2019, January 15–20). Pointconv: Deep convolutional networks on 3d point clouds. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00985 ↗
52. Sun, Y., Guo, X., and Yang, H. (2023). Win-Former: Window-Based Transformer for Maize Plant Point Cloud Semantic Segmentation. Agronomy, 13.10.3390/agronomy13112723 ↗
53. Zhang, L., and Zhang, K. (2023). Semi-Supervised Semantic Segmentation Network for Point Clouds Based on 3D Shape. Appl. Sci., 13.10.3390/app13063872 ↗
54. Wu, C., Zheng, J., Pfrommer, J., and Beyerer, J. (2023, January 17–24). Attention-Based Point Cloud Edge Sampling. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00516 ↗