MeshMosaic：通过局部到全局组装扩展艺术家网格生成
MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly
把高面数网格切成局部块、逐块自回归生成并用共享边界条件保证接缝一致，这套局部到全局的量化与组装策略可直接迁移到高分辨率网格/3D资产的生成与补全，绕开长序列与量化粒度瓶颈。
原文依据 MeshMosaic first segments shapes into patches, generating each patch autoregressively and leveraging shared boundary conditions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论将艺术家设计的网格扩展到高三角面数，对自回归生成模型而言仍然具有挑战性。现有的基于 Transformer 的方法受制于长序列瓶颈与有限的量化分辨率，其主要原因在于所需的 token 数量庞大以及量化粒度受限。这些问题导致无法忠实复现精细的几何细节与结构化的密度模式。我们提出 MeshMosaic，一种面向艺术家网格生成的新颖的局部到全局框架，可扩展到超过 10 万个三角面，大幅超越此前通常只能处理约 8 千个面的方法。MeshMosaic 首先将形状分割为多个图像块式的局部块，逐块自回归生成，并利用共享的边界条件来促进相邻区域之间的一致性、对称性与无缝连接。该策略通过对每个局部块单独量化，提升了向高分辨率网格扩展的能力，从而得到更对称、更有组织的网格密度与结构。在多个公开数据集上的大量实验表明，MeshMosaic 在几何保真度与用户偏好两方面均显著优于最优方法，支持更优的细节表示，并可用于真实应用中的实用网格生成。
英文原文摘要 1293 字符
Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resolution, primarily due to the large number of tokens required and constrained quantization granularity. These issues prevent faithful reproduction of fine geometric details and structured density patterns. We introduce MeshMosaic, a novel local-to-global framework for artist mesh generation that scales to over 100K triangles--substantially surpassing prior methods, which typically handle only around 8K faces. MeshMosaic first segments shapes into patches, generating each patch autoregressively and leveraging shared boundary conditions to promote coherence, symmetry, and seamless connectivity between neighboring regions. This strategy enhances scalability to high-resolution meshes by quantizing patches individually, resulting in more symmetrical and organized mesh density and structure. Extensive experiments across multiple public datasets demonstrate that MeshMosaic significantly outperforms state-of-the-art methods in both geometric fidelity and user preference, supporting superior detail representation and practical mesh generation for real-world applications.