Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.05745 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917563893547008 |
|---|---|
| author | Hu, Barry Shichen Liang, Siyun Paetzold, Johannes Nguyen, Huy H. Echizen, Isao Tang, Jiapeng |
| author_facet | Hu, Barry Shichen Liang, Siyun Paetzold, Johannes Nguyen, Huy H. Echizen, Isao Tang, Jiapeng |
| contents | We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input scales, then focus on a surface fitting method by which local point cloud neighborhoods are fitted to a geometric surface approximated by either a polynomial function or a multi-layer perceptron (MLP). However, fitting surfaces to fixed-order polynomial functions can suffer from overfitting or underfitting, and learning MLP-represented hyper-surfaces requires pre-generated per-point weights. To avoid these limitations, we first unify the design choices in previous works and then propose a simplified Transformer-based model to extract richer and more robust geometric features for the surface normal estimation task. Through extensive experiments, we demonstrate that our Transformer-based method achieves state-of-the-art performance on both the synthetic shape dataset PCPNet, and the real-world indoor scene dataset SceneNN, exhibiting more noise-resilient behavior and significantly faster inference. Most importantly, we demonstrate that the sophisticated hand-designed modules in existing works are not necessary to excel at the task of surface normal estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05745 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Surface Normal Estimation with Transformers Hu, Barry Shichen Liang, Siyun Paetzold, Johannes Nguyen, Huy H. Echizen, Isao Tang, Jiapeng Computer Vision and Pattern Recognition We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input scales, then focus on a surface fitting method by which local point cloud neighborhoods are fitted to a geometric surface approximated by either a polynomial function or a multi-layer perceptron (MLP). However, fitting surfaces to fixed-order polynomial functions can suffer from overfitting or underfitting, and learning MLP-represented hyper-surfaces requires pre-generated per-point weights. To avoid these limitations, we first unify the design choices in previous works and then propose a simplified Transformer-based model to extract richer and more robust geometric features for the surface normal estimation task. Through extensive experiments, we demonstrate that our Transformer-based method achieves state-of-the-art performance on both the synthetic shape dataset PCPNet, and the real-world indoor scene dataset SceneNN, exhibiting more noise-resilient behavior and significantly faster inference. Most importantly, we demonstrate that the sophisticated hand-designed modules in existing works are not necessary to excel at the task of surface normal estimation. |
| title | Surface Normal Estimation with Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.05745 |