EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
This addresses mesh generation for 3D modeling applications, offering improvements in quality and generalization, though it appears incremental as it builds on existing auto-regressive and auto-encoder methods.
The paper tackled the problem of incomplete, low-detail, and poorly generalizing auto-regressive mesh generation by proposing an Auto-regressive Auto-encoder model that generates high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512^3.
Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training latent diffusion models for better generalization. Extensive experiments demonstrate the superior quality, diversity, and generalization capabilities of our model in both point cloud and image-conditioned mesh generation tasks.