EdgeRunner：用于艺术网格生成的自回归自编码器
EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
AI总结：
针对自回归网格生成的不完整和泛化差问题，提出ArAE模型结合新颖网格标记化算法，高效压缩三角网格至定长潜在空间并训练扩散模型，生成高达4000面的高质量3D网格。
摘要：
当前自回归网格生成方法存在不完整、细节不足和泛化性差等问题。本文提出一种自回归自编码器（ArAE）模型，能够生成面数高达4,000、空间分辨率为$512^3$的高质量3D网格。我们引入一种新颖的网格标记化算法，将三角网格高效压缩为1D标记序列，显著提升训练效率。此外，该模型将变长三角网格压缩至定长潜在空间，从而支持训练潜在扩散模型以实现更好的泛化。大量实验表明，该模型在点云和图像条件网格生成任务中均展现出卓越的质量、多样性与泛化能力。
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
