Benchmarking and Analyzing Point Cloud Classification under Corruptions

Jiawei Ren, Liang Pan, Ziwei Liu
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18559-18575, 2022.

Abstract

3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness and generalizability. Our benchmark results show that although point cloud classification performance improves over time, the state-of-the-art methods are on the verge of being less robust. Based on the obtained observations, we propose several effective techniques to enhance point cloud classifier robustness. We hope our comprehensive benchmark, in-depth analysis, and proposed techniques could spark future research in robust 3D perception.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-ren22c, title = {Benchmarking and Analyzing Point Cloud Classification under Corruptions}, author = {Ren, Jiawei and Pan, Liang and Liu, Ziwei}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {18559--18575}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/ren22c/ren22c.pdf}, url = {https://proceedings.mlr.press/v162/ren22c.html}, abstract = {3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness and generalizability. Our benchmark results show that although point cloud classification performance improves over time, the state-of-the-art methods are on the verge of being less robust. Based on the obtained observations, we propose several effective techniques to enhance point cloud classifier robustness. We hope our comprehensive benchmark, in-depth analysis, and proposed techniques could spark future research in robust 3D perception.} }
Endnote
%0 Conference Paper %T Benchmarking and Analyzing Point Cloud Classification under Corruptions %A Jiawei Ren %A Liang Pan %A Ziwei Liu %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-ren22c %I PMLR %P 18559--18575 %U https://proceedings.mlr.press/v162/ren22c.html %V 162 %X 3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness and generalizability. Our benchmark results show that although point cloud classification performance improves over time, the state-of-the-art methods are on the verge of being less robust. Based on the obtained observations, we propose several effective techniques to enhance point cloud classifier robustness. We hope our comprehensive benchmark, in-depth analysis, and proposed techniques could spark future research in robust 3D perception.
APA
Ren, J., Pan, L. & Liu, Z.. (2022). Benchmarking and Analyzing Point Cloud Classification under Corruptions. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:18559-18575 Available from https://proceedings.mlr.press/v162/ren22c.html.

Related Material