EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Mesh Generation | Objaverse | Chamfer Distance0.053 | 18 | |
| Mesh Tokenization | 3D Mesh Representation | Compression Ratio0.47 | 12 | |
| Mesh Tokenization | Mesh Sequences | Compression Ratio0.47 | 7 |