FACE：一种基于面部的自回归表示，用于高保真和高效的网格生成
FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation
AI总结：
FACE提出了一种基于面的自回归表示方法，通过在面级别生成网格，显著提高3D网格生成的效率和保真度。
摘要：
自回归模型用于3D网格生成存在一个根本性的限制：它们将网格扁平化为长顶点坐标序列。这导致了极高的计算成本，阻碍了高效生成高保真几何结构。我们主张这个瓶颈源于在错误的语义层次上操作。我们引入了FACE，一种新的自回归自动编码器（ARAE）框架，通过在面级别生成网格来重新定义任务。我们的“一面对一token”策略将每个三角形面，即网格的基本构建块，视为一个单一的统一token。这种简单而强大的设计将序列长度减少了九倍，导致前所未有的压缩比为0.11，将之前的最先进水平减半。这种显著的效率提升并未牺牲质量；通过将我们的面级别解码器与强大的VecSet编码器相结合，FACE在标准基准上实现了最先进的重建质量。通过训练一个潜在扩散模型，进一步展示了所学潜在空间的多功能性，该模型实现了高保真的单图像到网格生成。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3D内容创作的门槛。
英文摘要：
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.
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。
