TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation

TL;DR

TetGAN is a novel convolutional neural network that generates tetrahedral meshes by encoding shapes into an irregular grid, enabling shape editing, synthesis, and topological variation.

Contribution

The paper introduces TetGAN, a new neural network architecture with tetrahedral convolution operations for explicit mesh connectivity synthesis.

Findings

Successfully encodes tetrahedral meshes into a meaningful latent space.

Enables shape editing and synthesis through learned features.

Supports variable topological genus in generated meshes.

Abstract

We present TetGAN, a convolutional neural network designed to generate tetrahedral meshes. We represent shapes using an irregular tetrahedral grid which encodes an occupancy and displacement field. Our formulation enables defining tetrahedral convolution, pooling, and upsampling operations to synthesize explicit mesh connectivity with variable topological genus. The proposed neural network layers learn deep features over each tetrahedron and learn to extract patterns within spatial regions across multiple scales. We illustrate the capabilities of our technique to encode tetrahedral meshes into a semantically meaningful latent-space which can be used for shape editing and synthesis. Our project page is at https://threedle.github.io/tetGAN/.