NASM: Neural Anisotropic Surface Meshing

TL;DR

NASM introduces a deep learning framework that uses a high-dimensional embedding space and graph neural networks to efficiently generate anisotropic surface meshes, capturing sharp features and curvature with improved scalability.

Contribution

The paper presents the first deep learning approach utilizing a high-dimensional Euclidean embedding for 3D anisotropic surface meshing, enhancing feature preservation and computational efficiency.

Findings

Outperforms state-of-the-art methods on Thingi10K dataset

Effectively captures sharp geometric features

Demonstrates scalability on large 3D shape datasets

Abstract

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.