English

EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation

Computer Vision and Pattern Recognition 2024-09-27 v1

Abstract

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 5123512^3. 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.

Keywords

Cite

@article{arxiv.2409.18114,
  title  = {EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation},
  author = {Jiaxiang Tang and Zhaoshuo Li and Zekun Hao and Xian Liu and Gang Zeng and Ming-Yu Liu and Qinsheng Zhang},
  journal= {arXiv preprint arXiv:2409.18114},
  year   = {2024}
}

Comments

Project Page: https://research.nvidia.com/labs/dir/edgerunner/

R2 v1 2026-06-28T18:58:34.423Z