Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.01331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914664360706048 |
|---|---|
| author | Luo, Shuqing Gao, Wei |
| author_facet | Luo, Shuqing Gao, Wei |
| contents | We propose a general method for deep learning based point cloud analysis, which is invariant to rotation on the inputs. Classical methods are vulnerable to rotation, as they usually take aligned point clouds as input. Principle Component Analysis (PCA) is a practical approach to achieve rotation invariance. However, there are still some gaps between theory and practical algorithms. In this work, we present a thorough study on designing rotation invariant algorithms for point cloud analysis. We first formulate it as a permutation invariant problem, then propose a general framework which can be combined with any backbones. Our method is beneficial for further research such as 3D pre-training and multi-modal learning. Experiments show that our method has considerable or better performance compared to state-of-the-art approaches on common benchmarks. Code is available at https://github.com/luoshuqing2001/RI_framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A general framework for rotation invariant point cloud analysis Luo, Shuqing Gao, Wei Computer Vision and Pattern Recognition We propose a general method for deep learning based point cloud analysis, which is invariant to rotation on the inputs. Classical methods are vulnerable to rotation, as they usually take aligned point clouds as input. Principle Component Analysis (PCA) is a practical approach to achieve rotation invariance. However, there are still some gaps between theory and practical algorithms. In this work, we present a thorough study on designing rotation invariant algorithms for point cloud analysis. We first formulate it as a permutation invariant problem, then propose a general framework which can be combined with any backbones. Our method is beneficial for further research such as 3D pre-training and multi-modal learning. Experiments show that our method has considerable or better performance compared to state-of-the-art approaches on common benchmarks. Code is available at https://github.com/luoshuqing2001/RI_framework. |
| title | A general framework for rotation invariant point cloud analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.01331 |