Autoregressive models for 3D mesh generation suffer from a fundamental limitation: they flatten meshes into long vertex-coordinate sequences. This results in prohibitive computational costs, hindering the efficient synthesis of high-fidelity geometry. We argue this bottleneck stems from operating at the wrong semantic level. We introduce FACE, a novel Autoregressive Autoencoder (ARAE) framework that reconceptualizes the task by generating meshes at the face level. Our one-face-one-token strategy treats each triangle face, the fundamental building block of a mesh, as a single, unified token. This simple yet powerful design reduces the sequence length by a factor of nine, leading to an unprecedented compression ratio of 0.11, halving the previous state-of-the-art. This dramatic efficiency gain does not compromise quality; by pairing our face-level decoder with a powerful VecSet encoder, FACE achieves state-of-the-art reconstruction quality on standard benchmarks. The versatility of the learned latent space is further demonstrated by training a latent diffusion model that achieves high-fidelity, single-image-to-mesh generation. FACE provides a simple, scalable, and powerful paradigm that lowers the barrier to high-quality structured 3D content creation.
@article{arxiv.2603.01515,
title = {FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation},
author = {Hanxiao Wang and Yuan-Chen Guo and Ying-Tian Liu and Zi-Xin Zou and Biao Zhang and Weize Quan and Ding Liang and Yan-Pei Cao and Dong-Ming Yan},
journal= {arXiv preprint arXiv:2603.01515},
year = {2026}
}