Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module

TL;DR

This paper introduces Set-Mixer, a novel network architecture component that improves point cloud recognition robustness against noise by using spatial sorting and set-mixing aggregation, inspired by 2D token-mixing techniques.

Contribution

The paper proposes Set-Mixer, a new noise-robust aggregation module with a sorting strategy for permutation invariance, addressing noise and unordered structure in point cloud recognition.

Findings

Set-Mixer significantly improves recognition accuracy on noisy point clouds.

The sorting strategy ensures permutation invariance and spatial consistency.

Experiments on ModelNet40-C demonstrate enhanced robustness to noise.

Abstract

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing robustness through various strategies, there still remains a gap in comprehensive analyzes from the standpoint of network architecture design. Unlike traditional methods that rely on generic techniques, our approach optimizes model robustness to noise corruption through network architecture design. Inspired by the token-mixing technique applied in 2D images, we propose Set-Mixer, a noise-robust aggregation module which facilitates communication among all points to extract geometric shape information and mitigating the influence of individual noise points. A sorting strategy is designed to enable our module to be invariant to point permutation, which also tackles the unordered structure of point cloud and introduces consistent relative spatial information. Experiments conducted on ModelNet40-C indicate that Set-Mixer significantly enhances the model performance on noisy point clouds, underscoring its potential to advance real-world applicability in 3D recognition and perception tasks.