Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929592273469440 |
|---|---|
| author | Zhang, Dingxin Yu, Jianhui Xue, Tengfei Zhang, Chaoyi Liu, Dongnan Cai, Weidong |
| author_facet | Zhang, Dingxin Yu, Jianhui Xue, Tengfei Zhang, Chaoyi Liu, Dongnan Cai, Weidong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10806 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module Zhang, Dingxin Yu, Jianhui Xue, Tengfei Zhang, Chaoyi Liu, Dongnan Cai, Weidong Computer Vision and Pattern Recognition 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. |
| title | Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.10806 |