Guoquan Xu
ABSTRACT
The tasks of point cloud analysis are very challenging. Designing efficient convolution operation is the key to accomplish these tasks. In order to capture the structure information, neighborhood usually needs to be considered when designing convolution. At present, most of the works adopt K-Nearest Neighbor or ball query to construct neighborhood. However, these two methods only focus on the spatial distance relationship and ignore the long-distance dependence between points. In this paper, Learnable-Graph Convolutional Neural Network (LG-CNN) is proposed, which can adaptively search the backbone graph of objects. The key of LG-CNN is to design a learning-based neighborhood search method, which adaptively searches the overall backbone information of the object for each central point. Compared with updating the central point through local information aggregation, the effect of using backbone information to update the central point is better. Moreover, a graph convolution is designed to adaptively obtain the unique relationship between points and capture the diversified links between different neighbors. The challenging benchmark experiments of three tasks verify LG-CNN achieves competitive results.
- Qi, C. R. Su, H. and Guibas, L. J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652-660. IEEE, Honolulu, HI, USA. 2017.Google Scholar
- Qi, C. R. Yi, L. Su, H. and Guibas, L. J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (NIPS), pp. 5105-5144. NIPS, Long Beach, California, USA. 2017.Google Scholar
- Wang, Y. Sun, Y. Liu, Z. Sarma, S. Bronstein, M. and Solomon, J.: Dynamic graph cnn for learning on point clouds. ACM TOG. vol. 38 (5), 1-12, 2019.Google ScholarDigital Library
- Liu, Y. C. Fan, B. Xiang, S. and Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-10. IEEE, Long Beach, CA, USA. 2019.Google ScholarCross Ref
- Thomas, H. Qi, C. R. Deschaud, J. Marcotegui, B. Goulette, F. and Guibas, L. J.: Kpconv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 6411-6420. IEEE, Seoul, Korea (South). 2019.Google ScholarCross Ref
- Maturana, D. and Scherer, S.: Voxnet: a 3d convolutional neural network for real-time object recognition. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 922-928. IEEE, Hamburg, Germany. 2015.Google ScholarDigital Library
- Shen, Y. Feng, C. Yang, Y. and Tian, D.: Mining point cloud local structures by kernel correlation and graph pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4548-4557. IEEE, Salt Lake City, UT, USA. 2018.Google ScholarCross Ref
- Atzmon, M. Maron, H. and Lipman, Y.: Point convolutional neural networks by extension operators. ACM Transactions on Graphics. vol. 37(4), 1-14, 2018.Google ScholarDigital Library
- Lin, Y. Yan, Z. Huang, H. Du, D. Liu, L. Cui, S. and Han, X.: Fpconv: learning local flattening for point convolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4292-4301. IEEE, Seattle, WA, USA. 2020.Google ScholarCross Ref
- Liu, Z. Hu, H. Cao, Y. Zhang, Z. and Tong, X.: A closer look at local aggregation operators in point cloud analysis. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 326-342. Springer, HongKong, China. 2020.Google ScholarDigital Library
- Li, Y. Bu, R. Sun, M. and Chen, B.: Pointcnn: convolution on x-transformed points. In: Advances in Neural Information Processing Systems (NIPS), pp. 828-838. IEEE, 2018.Google Scholar
- Zhou, H. Feng, Y. Fang, M. Wei, M. Qin, J. and Lu, T.: Adaptive graph convolution for point cloud analysis. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 244-253. IEEE, Montreal, QC, Canada. 2022.Google Scholar
- Guo, H. Wang, J. Gao, Y. Li, J. and Lu, H.: Multi-view 3D object retrieval with deep embedding network. IEEE Trans. Image Processing. vol. 25 (12), 5526-5537, 2016.Google ScholarDigital Library
- Choy, C. Gwak, J. and Savarese, S.: 4d spatio-temporal convnets: minkowski convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3070-3079. IEEE, Long Beach, CA, USA. 2019.Google ScholarCross Ref
- Su, H. Jampani, V. Sun, D. Maji, S. Kalogerakis, E. Yang, M. and Kautz, J.: Splatnet: sparse lattice networks for point cloud processing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2530-2539. IEEE, Salt Lake City, UT, USA. 2018.Google ScholarCross Ref
- Lin, Z. Huang, S. and Wang, Y.: Convolution in the cloud: Learning deformable kernels in 3d graph convolution networks for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1797-1806. IEEE, Seattle, WA, USA. 2020.Google ScholarCross Ref
- Feng, M. Zhang, L. Lin, X. Gilani, S. and Mian, A.: Point attention network for semantic segmentation of 3d point clouds. Pattern Recognition. vol. 107, 107446. 2020.Google Scholar
- Wu, Z. Song, S. Khosla, A. Yu, F. Zhang, L. Tang, X. and Xiao, J.: 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912-1920. IEEE, Boston, MA, USA. 2015.Google Scholar
- Yi, L. Kim, V. Ceylan, D. Shen, I. Yan, M. Su, H. Lu, C. Huang, Q. Sheffer, A. and Guibas, L. J.: A scalable active framework for region annotation in 3d shape collections. ACMTrans. Graph. vol. 35 (6), 1-12. 2016.Google ScholarDigital Library
- Uy, M. Pham, Q. Hua, B. Nguyen, T. and Yeung, S.: Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1588-1597. IEEE, Seoul, Korea (South). 2019.Google ScholarCross Ref
- Li, J. Chen, B. M. and Lee, G. H.: So-net: Self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9397-9406. IEEE, Salt Lake City, UT, USA. 2018.Google ScholarCross Ref
- Mao, J. Wang, X. and Li, H.: Interpolated convolutional networks for 3d point cloud understanding. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1578-1587. IEEE, Seoul, Korea (South) (2019).Google ScholarCross Ref
- Yan, X. Zheng, C. Li, Z. Wang, S. and Cui, S.: Pointasnl: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5588-5597. IEEE, Seattle, WA, USA. 2020.Google ScholarCross Ref
- Wu, W. Qi, Z. and Li, F.: Pointconv: deep convolutional networks on 3d point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9621-9630. IEEE, Long Beach, CA, USA. 2019.Google ScholarCross Ref
Index Terms
- Learnable-graph convolutional neural network for point cloud analysis
Recommendations
KeypointNet: Ranking Point Cloud for Convolution Neural Network
Image and GraphicsAbstractIn recent years, convolutional neural networks on point clouds have greatly improved the performance of point cloud classification and segmentation. However, the irregularity and disorder of point clouds make the convolution operation ill-suited ...
Learning Graph-Convolutional Representations for Point Cloud Denoising
Computer Vision – ECCV 2020AbstractPoint clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-...
Edge-preserving image denoising using a deep convolutional neural network
Highlights- This paper makes use of a deep CNN for image denoising.
- The network is trained ...
AbstractThis paper introduces a novel denoising approach making use of a deep convolutional neural network to preserve image edges. The network is trained by using the edge map obtained from the well-known Canny algorithm and aims at ...
Comments