R-PointNet: Robust 3D Object Recognition Network for Real-World Point Clouds Corruption
Source abstract
Abstract
Point clouds obtained with 3D scanners in realistic scenes inevitably contain corruption, including noise and outliers. Traditional algorithms for cleaning point cloud corruption require the selection of appropriate parameters based on the characteristics of the scene, data, and algorithm, which means that their performance is highly dependent on the experience and adaptation of the algorithm itself to the application. Three-dimensional object recognition networks for real-world recognition tasks can take the raw point cloud as input and output the recognition results directly. Current 3D object recognition networks generally acquire uniform sampling points by farthest point sampling (FPS) to extract features. However, sampled defective points from FPS lower the recognition accuracy by affecting the aggregated global feature. To deal with this issue, we design a compensation module, named offset-adjustment (OA). It can adaptively adjust the coordinates of sampled defective points based on neighbors and improve local feature extraction to enhance network robustness. Furthermore, we employ the OA module to build an end-to-end network based on PointNet++ framework for robust point cloud recognition, named R-PointNet. Experiments show that R-PointNet reaches state-of-the-art performance by 92.5% of recognition accuracy on ModelNet40, and significantly outperforms previous networks by 3–7.7% on the corruption dataset ModelNet40-C for robustness benchmark.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Shape Modeling and Analysis · 3D Surveying and Cultural Heritage · Advanced Numerical Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Engineering and Science, Shanghai University, Shanghai 201900, China
Funding
Shanghai Science and Technology Committee
References (31)
Show source-provided references
1. Recognition of Point Sets Objects in Realistic Scenes
2. Pedestrian Detection and Tracking Using Three-dimensional LADAR Data10.1177/0278364910370216 ↗
3. Kidono, K., Miyasaka, T., Watanabe, A., Naito, T., and Miura, J. (2011, January 5–9). Pedestrian Recognition Using High-definition LIDAR. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Baden-Baden, Germany.10.1109/IVS.2011.5940433 ↗
4. Rusu, R.B., Blodow, N., Marton, Z.C., and Beetz, M. (2009, January 10–15). Close-range Scene Segmentation and Reconstruction of 3D Point Cloud Maps for Mobile Manipulation in Domestic Environments. Proceedings of the IEEE RSJ International Conference on Intelligent Robots and Systems, St. Louis, MO, USA.10.1109/IROS.2009.5354683 ↗
5. Analysis and Observations From the First Amazon Picking Challenge10.1109/TASE.2016.2600527 ↗
6. A review of algorithms for filtering the 3D point cloud10.1016/j.image.2017.05.009 ↗
7. Outlier analysis
8. Qi, C.R., 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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.
9. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4–9). Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Red Hook, NY, USA.
10. Wu, Z.R., Song, S.R., Khosla, A., Yu, F., Zhang, L.G., Tang, X.O., and Xiao, J.X. (2015, January 7–12). 3D ShapeNets: A Deep Representation for Volumetric Shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
11. Sun, J., Zhang, Q., Kailkhura, B., Yu, Z., Xiao, C., and Morley Mao, Z.J. (2022). Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions. arXiv.
12. Dynamic Graph CNN for Learning on Point Clouds10.1145/3326362 ↗
13. PCT: Point cloud transformer10.1007/s41095-021-0229-5 ↗
14. Outliers in statistical data:, V. Barnett and T. Lewis1994, 3rd edition, (John Wiley & Sons, Chichester), 584 pp., £55.00, ISBN 0-471-93094-610.1016/0169-2070(95)00625-7 ↗
15. Robust statistics for outlier detection10.1002/widm.2 ↗
16. Edge-Aware Point Set Resampling10.1145/2421636.2421645 ↗
17. Hermosilla, P., Ritschel, T., Vazquez, P.P., Vinacua, A., Ropinski, T., and Assoc Comp, M. (2018, January 4–7). Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. Proceedings of the 11th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SA), Tokyo, Japan.
18. Yang, J.C., Zhang, Q., Ni, B.B., Li, L.G., Liu, J.X., Zhou, M.D., Tian, Q., and Soc, I.C. (2019, January 20–25). Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling. Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR.2019.00344 ↗
19. Li, J.X., Chen, B.M., and Lee, G.H. (2018, January 18–23). SO-Net: Self-Organizing Network for Point Cloud Analysis. Proceedings of the 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00979 ↗
20. Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L.J. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
21. Xiao, C.X., and Wachs, J. (2021, January 3–8). Triangle-Net: Towards Robustness in Point Cloud Learning. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.10.1109/WACV48630.2021.00087 ↗
22. Deep Learning for 3D Point Clouds: A Survey10.1109/TPAMI.2020.3005434 ↗
23. Maturana, D., and Scherer, S. (October, January 28). VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.
24. Le, T., and Duan, Y. (2018, January 18–23). PointGrid: A Deep Network for 3D Shape Understanding. Proceedings of the 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00959 ↗
25. 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 ↗
26. Feng, Y.F., Zhang, Z.Z., Zhao, X.B., Ji, R.R., and Gao, Y. (2018, January 18–23). GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition. Proceedings of the 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00035 ↗
27. Li, Y.Y., Bu, R., Sun, M.C., Wu, W., Di, X.H., and Chen, B.Q. (2018, January 3–8). PointCNN: Convolution On X -Transformed Points. Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS), Montréal, QC, Canada.
28. Liu, Y.C., Fan, B., Xiang, S.M., and Pan, C.H. (2019, January 15–20). Relation-Shape Convolutional Neural Network for Point Cloud Analysis. Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00910 ↗
29. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention Is All You Need. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA.
30. Goyal, A., Law, H., Liu, B.W., Newel, A., and Deng, J. (2021, January 18–21). Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline. Proceedings of the 38th International Conference on Machine Learning (ICML), Virtual.
31. Ren, J.W., Pan, L., and Liu, Z.W. (2022, January 17–23). Benchmarking and Analyzing Point Cloud Classification under Corruptions. Proceedings of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA.