|国家预印本平台
首页|EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Gang Zeng、Zekun Hao、Zhaoshuo Li、Ming-Yu Liu、Jiaxiang Tang、Xian Liu、Qinsheng Zhang

计算技术、计算机技术

Gang Zeng,Zekun Hao,Zhaoshuo Li,Ming-Yu Liu,Jiaxiang Tang,Xian Liu,Qinsheng Zhang.EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation[EB/OL].(2024-09-26)[2025-07-25].https://arxiv.org/abs/2409.18114.点此复制

评论