NASM: Neural Anisotropic Surface Meshing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929571015688192 |
|---|---|
| author | Li, Hongbo Zhu, Haikuan Zhong, Sikai Wang, Ningna Lin, Cheng Guo, Xiaohu Xin, Shiqing Wang, Wenping Hua, Jing Zhong, Zichun |
| author_facet | Li, Hongbo Zhu, Haikuan Zhong, Sikai Wang, Ningna Lin, Cheng Guo, Xiaohu Xin, Shiqing Wang, Wenping Hua, Jing Zhong, Zichun |
| contents | This paper introduces a new learning-based method, NASM, for anisotropic surface meshing. Our key idea is to propose a graph neural network to embed an input mesh into a high-dimensional (high-d) Euclidean embedding space to preserve curvature-based anisotropic metric by using a dot product loss between high-d edge vectors. This can dramatically reduce the computational time and increase the scalability. Then, we propose a novel feature-sensitive remeshing on the generated high-d embedding to automatically capture sharp geometric features. We define a high-d normal metric, and then derive an automatic differentiation on a high-d centroidal Voronoi tessellation (CVT) optimization with the normal metric to simultaneously preserve geometric features and curvature anisotropy that exhibit in the original 3D shapes. To our knowledge, this is the first time that a deep learning framework and a large dataset are proposed to construct a high-d Euclidean embedding space for 3D anisotropic surface meshing. Experimental results are evaluated and compared with the state-of-the-art in anisotropic surface meshing on a large number of surface models from Thingi10K dataset as well as tested on extensive unseen 3D shapes from Multi-Garment Network dataset and FAUST human dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23109 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NASM: Neural Anisotropic Surface Meshing Li, Hongbo Zhu, Haikuan Zhong, Sikai Wang, Ningna Lin, Cheng Guo, Xiaohu Xin, Shiqing Wang, Wenping Hua, Jing Zhong, Zichun Computer Vision and Pattern Recognition Computational Geometry Graphics This paper introduces a new learning-based method, NASM, for anisotropic surface meshing. Our key idea is to propose a graph neural network to embed an input mesh into a high-dimensional (high-d) Euclidean embedding space to preserve curvature-based anisotropic metric by using a dot product loss between high-d edge vectors. This can dramatically reduce the computational time and increase the scalability. Then, we propose a novel feature-sensitive remeshing on the generated high-d embedding to automatically capture sharp geometric features. We define a high-d normal metric, and then derive an automatic differentiation on a high-d centroidal Voronoi tessellation (CVT) optimization with the normal metric to simultaneously preserve geometric features and curvature anisotropy that exhibit in the original 3D shapes. To our knowledge, this is the first time that a deep learning framework and a large dataset are proposed to construct a high-d Euclidean embedding space for 3D anisotropic surface meshing. Experimental results are evaluated and compared with the state-of-the-art in anisotropic surface meshing on a large number of surface models from Thingi10K dataset as well as tested on extensive unseen 3D shapes from Multi-Garment Network dataset and FAUST human dataset. |
| title | NASM: Neural Anisotropic Surface Meshing |
| topic | Computer Vision and Pattern Recognition Computational Geometry Graphics |
| url | https://arxiv.org/abs/2410.23109 |