Abstract
In the recent years, the problem of 3D shape analysis in the point cloud is considered as one of the challenging research topics in the field of computer vision. The major issues here are effective representation of the 3D information, meaningful feature extraction and subsequent task of classification. In this research paper, a deep learning-based network called Drop Channel Graph Neural Network (DC-GNN) is proposed for object classification and part segmentation. The DC-GNN model employs the idea of k-NN-based drop channel with hierarchical feature selection approach at each layer for dynamic graph construction, and further, with the help of Multi-Layer Perceptron Networks accomplishes the task of object classification. The same DC-GNN model is extended to carry out part segmentation in the point cloud data using the ShapeNet-Part benchmark dataset. The proposed network reports the state-of-the-art classification accuracy of 93.64% with ModelNet-40 dataset (Source-Code-https://github.com/merazlab/DC-GNN).
Similar content being viewed by others
References
Kutila M, Pyykönen P, Ritter W, Sawade O, Schäufele B (2016) Automotive lidar sensor development scenarios for harsh weather conditions, In: 2016 IEEE 19th international conference on intelligent transportation systems (ITSC). IEEE, pp 265–270
Aubry M, Schlickewei U, Cremers D (2011) The wave kernel signature: a quantum mechanical approach to shape analysis, In: 2011 IEEE international conference on computer vision workshops (ICCV workshops). IEEE, pp 1626–1633
Sun J, Ovsjanikov M, Guibas L (2009) A concise and provably informative multi-scale signature based on heat diffusion, In: Computer graphics forum, vol. 28, no. 5. Wiley, pp 1383–1392
Rusu RB, Blodow N, Marton ZC, Beetz M (2008) Aligning point cloud views using persistent feature histograms, In: 2008 IEEE/RSJ international conference on intelligent robots and systems. IEEE, pp 3384–3391
Johnson AE, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans Pattern Anal Mach Intell 21(5):433–449
Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1912–1920
Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652–660
Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv:1706.02413
Simonovsky M, Komodakis N (July 2017) Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Xu Q, Sun X, Wu C-Y, Wang P, Neumann U (2020) Grid-gcn for fast and scalable point cloud learning, In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5661–5670
Wang Y, Sun Y, Liu Z, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph cnn for learning on point clouds. Acm Trans Graph (tog) 38(5):1–12
Maturana D, Scherer S (2015) Voxnet: a 3d convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 922–928
Klokov R, Lempitsky V (Oct 2017) 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)
Wang P-S, Liu Y, Guo Y-X, Sun C-Y, Tong X (2017) O-cnn: octree-based convolutional neural networks for 3d shape analysis. ACM Trans Graph (TOG) 36(4):1–11
Riegler G, Osman Ulusoy A, Geiger A (2017) Octnet: learning deep 3d representations at high resolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3577–3586
Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K (2014) Densenet: implementing efficient convnet descriptor pyramids. arXiv:1404.1869
Mao J, Wang X, Li H (2019) Interpolated convolutional networks for 3d point cloud understanding. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1578–1587
Lan S, Yu R, Yu G, Davis LS (2019) Modeling local geometric structure of 3d point clouds using geo-cnn. In: Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, pp 998–1008
Yan X, Zheng C, Li Z, Wang S, Cui S (2020) Pointasnl: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5589–5598
Klokov R, Lempitsky V (2017) Escape from cells: deep kd-networks for the recognition of 3d point cloud models. In: Proceedings of the IEEE international conference on computer vision, pp 863–872
Li J, Chen B, Lee GH (2018) So-net: self-organizing network for point cloud analysis .In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp 9397–9406
Yi L, Kim VG, Ceylan D, Shen I-C, Yan M, Su H, Lu C, Huang Q, Sheffer A, Guibas L (2016) A scalable active framework for region annotation in 3d shape collections. ACM Trans Graph (ToG) 35(6):1–12
Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46(3):175–185
Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. arXiv:1506.02025
Le T, Duan Y (2018) Pointgrid: a deep network for 3d shape understanding. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp 9204–9214
Atzmon M, Maron H, Lipman Y (2018) Point convolutional neural networks by extension operators. arXiv:1803.10091
Li Y, Bu R, Sun M, Wu W, Di X, Chen B (2018) Pointcnn: convolution on x-transformed points. In: NeurIPS
Wu W, Qi Z, Li F (2019) Pointconv: deep convolutional networks on 3d point clouds. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 9613–9622
Komarichev A, Zhong Z, Hua J (2019) A-cnn: annularly convolutional neural networks on point clouds. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7421–7430
Guo M-H, Cai J-X, Liu Z-N, Mu T-J, Martin RR, Hu S-M (2020) Pct: point cloud transformer. arXiv:2012.09688
Thomas H, Qi CR, Deschaud J-E, Marcotegui B, Goulette F, Guibas LJ (2019) Kpconv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 6411–6420
Liu Y, Fan B, Xiang S, Pan C (2019) Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8895–8904
Acknowledgements
The author gratefully acknowledges the support of Central Computing Facility (CCF) of Indian Institute of Information Technology Allahabad, and the resources provided by PARAM Shivay Facility under the National Supercomputer Mission, at the IIT-BHU Varanasi. This research work is carried out with the support received from the Ministry of Education, Government of India.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Meraz, M., Ansari, M.A., Javed, M. et al. DC-GNN: drop channel graph neural network for object classification and part segmentation in the point cloud. Int J Multimed Info Retr 11, 123–133 (2022). https://doi.org/10.1007/s13735-022-00236-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13735-022-00236-7