Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

TL;DR

This paper introduces ModelNet40-C, a comprehensive benchmark for evaluating the robustness of 3D point cloud recognition models against common corruptions, revealing significant performance gaps and proposing effective mitigation strategies.

Contribution

It presents the first extensive benchmark for 3D point cloud corruption robustness and offers insights into architecture choices and training strategies that enhance robustness.

Findings

Transformer architectures with proper training are most robust.

Significant performance gap exists between clean and corrupted data.

Simple augmentation and adaptation methods improve robustness.

Abstract

Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the first comprehensive benchmark on 3D point cloud corruption robustness, consisting of 15 common and realistic corruptions. Our evaluation shows a significant gap between the performances on ModelNet40 and ModelNet40-C for state-of-the-art (SOTA) models. To reduce the gap, we propose a simple but effective method by combining PointCutMix-R and TENT after evaluating a wide range of augmentation and test-time adaptation strategies. We identify a number of critical insights for future studies on corruption robustness in point cloud recognition. For instance, we unveil that Transformer-based architectures with proper training recipes achieve the strongest robustness. We hope our in-depth analysis will motivate the development of robust training strategies or architecture designs in the 3D point cloud domain. Our codebase and dataset are included in https://github.com/jiachens/ModelNet40-C