E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916269310083072 |
|---|---|
| author | Wang, Hanxiao Zhao, Mingyang Quan, Weize Chen, Zhen Yan, Dong-ming Wonka, Peter |
| author_facet | Wang, Hanxiao Zhao, Mingyang Quan, Weize Chen, Zhen Yan, Dong-ming Wonka, Peter |
| contents | Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in inefficient learning of symmetric patterns. To address this issue, we propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work and improves the accuracy. Further, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively utilizes the local properties of point clouds. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin. We improve RMSE by 4% on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00347 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network Wang, Hanxiao Zhao, Mingyang Quan, Weize Chen, Zhen Yan, Dong-ming Wonka, Peter Computer Vision and Pattern Recognition Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in inefficient learning of symmetric patterns. To address this issue, we propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work and improves the accuracy. Further, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively utilizes the local properties of point clouds. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin. We improve RMSE by 4% on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset. |
| title | E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00347 |