Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 29 functions out of this paper's own repositories and ran 22 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• jiachens/ModelNet40-C — marked official in Papers with Code; named in the paper
• RF5/CurveNet
• dogyoonlee/RSMix
• dogyoonlee/RSMix-official
• hamidreza-dastmalchi/3dd-tta
• tiangexiang/CurveNet

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.12296")
get_code_for_paper("2201.12296")
have("2201.12296")

Connect an agent — have() is free.