Benchmarking and Analyzing Point Cloud Classification under Corruptions

TL;DR

This paper systematically benchmarks point cloud classification robustness under various corruptions, revealing current methods' fragility and proposing techniques to improve their resilience for real-world applications.

Contribution

It provides a comprehensive taxonomy of 3D corruptions, evaluates model robustness, and introduces techniques to enhance point cloud classifier resilience.

Findings

State-of-the-art models are less robust to corruptions.

Benchmark results highlight the need for robustness improvements.

Proposed techniques effectively enhance model robustness.

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.