3DMeshNet: A Three-Dimensional Differential Neural Network for Structured Mesh Generation

TL;DR

3DMeshNet is a neural network-based method that efficiently generates high-quality 3D structured meshes by embedding differential equations into its loss function, significantly reducing training time and meshing overhead.

Contribution

The paper introduces 3DMeshNet, a novel neural network approach that formulates mesh generation as an unsupervised optimization problem incorporating differential equations.

Findings

Outperforms existing neural network-based methods in speed and quality.

Reduces training time by up to 85%.

Lowers meshing overhead by 4 to 8 times.

Abstract

Mesh generation is a crucial step in numerical simulations, significantly impacting simulation accuracy and efficiency. However, generating meshes remains time-consuming and requires expensive computational resources. In this paper, we propose a novel method, 3DMeshNet, for three-dimensional structured mesh generation. The method embeds the meshing-related differential equations into the loss function of neural networks, formulating the meshing task as an unsupervised optimization problem. It takes geometric points as input to learn the potential mapping between parametric and computational domains. After suitable offline training, 3DMeshNet can efficiently output a three-dimensional structured mesh with a user-defined number of quadrilateral/hexahedral cells through the feed-forward neural prediction. To enhance training stability and accelerate convergence, we integrate loss function reweighting through weight adjustments and gradient projection alongside applying finite difference methods to streamline derivative computations in the loss. Experiments on different cases show that 3DMeshNet is robust and fast. It outperforms neural network-based methods and yields superior meshes compared to traditional mesh partitioning methods. 3DMeshNet significantly reduces training times by up to 85% compared to other neural network-based approaches and lowers meshing overhead by 4 to 8 times relative to traditional meshing methods.