EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Jiaxiang Tang, Zhaoshuo Li, Zekun Hao, Xian Liu, Gang Zeng, Ming-Yu Liu, Qinsheng Zhang
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 $512^3$. 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.
BibTeX
@inproceedings{
tang2025edgerunner,
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},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=81cta3WQVI}
}