Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module
This work addresses robustness issues for real-world 3D recognition tasks, representing an incremental improvement in network architecture design.
The paper tackles the problem of noise corruption in point cloud recognition by proposing Set-Mixer, a noise-robust aggregation module, which significantly enhances model performance on noisy datasets like ModelNet40-C.
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.