FACE：一种基于面的自回归表示用于高保真高效网格生成
FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation
将网格生成从顶点级序列改为面级 token，序列长度降低 9 倍，为自回归 3D 生成提供高效表示；其面级解码器与 VecSet 编码器结合可复用于单图到网格的潜扩散生成。
原文依据 Our one-face-one-token strategy treats each triangle face, the fundamental building block of a mesh, as a single, unified token.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论用于三维网格生成的自回归模型存在一个根本性局限：它们将网格展平为长顶点坐标序列。这导致计算成本过高，阻碍了高保真几何的高效合成。我们认为这一瓶颈源于在错误的语义层级上操作。我们提出 FACE，一种新颖的自回归自编码器（ARAE）框架，通过面级别生成网格来重新概念化该任务。我们的“一面一 token”策略将每个三角面——网格的基本构建块——视为单个统一 token。这一简单而强大的设计将序列长度降低九倍，带来前所未有的 0.11 压缩比，将此前最优水平减半。这种显著的效率提升并未牺牲质量；通过将面级解码器与强大的 VecSet 编码器配对，FACE 在标准基准上实现了最优的重建质量。通过训练一个潜扩散模型实现高保真单图到网格生成，进一步展示了所学潜空间的通用性。FACE 提供了一种简单、可扩展且强大的范式，降低了高质量结构化三维内容创作的门槛。
英文原文摘要 1270 字符
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.