Benchmarking and Analyzing Point Cloud Classification under Corruptions
This work addresses robustness issues in 3D perception for applications like autonomous driving and robotics, but it is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of point cloud classification under real-world corruptions by benchmarking and analyzing the robustness of existing models, finding that state-of-the-art methods are becoming less robust despite performance improvements.
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.