Meshy T2：基于流匹配的快速原生网格生成

摘要

多边形网格是现代三维管线中的标准表面表示方法，生成具有艺术家风格拓扑的高质量网格对于影视、游戏和交互式三维应用至关重要。主流方法将网格序列化为令牌序列并以自回归方式解码，这种方案推理速度慢且对误差累积敏感，难以满足交互式资产创建的实际需求。我们提出Meshy T2，一个基于流匹配构建的快速原生网格生成框架。其核心是顶点集网格变分自编码器（VAE），它将网格编码为每个顶点一个连续潜变量令牌，并一次性解码顶点、边连接关系和面缠绕顺序，在无需顶点量化或焊接的情况下保持高精度几何和艺术家创作的拓扑结构。生成过程采用由粗到精的两级流匹配级联：首先，图像条件体素流将整体形状勾勒为粗占用骨架；随后，网格流以图像、骨架及所请求的顶点预算为条件，用逐顶点潜变量令牌填充骨架。该设计实现了三项实用能力：通过并行的基于流合成实现交互式生成速度；通过所请求的顶点预算实现有效的面数控制；以及对多部件资产的天然支持，各部件直接由生成的连接关系涌现。在实验中，Meshy T2达到了最先进的几何保真度，并在中位数6秒内完成端到端的图像到网格生成，比自回归基线快一个数量级以上。代码和权重将在 https://github.com/meshy-dev/meshy-t2 上提供。

English

Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D applications. Mainstream approaches serialize a mesh into a token sequence and decode it autoregressively, which is slow at inference and sensitive to error accumulation, making them impractical for interactive asset creation. We present Meshy T2, a fast native mesh generation framework built on flow matching. At its core is a vertex-set mesh VAE that encodes a mesh into one continuous latent token per vertex and decodes vertices, edge connectivity, and face winding order in a single pass, preserving high-precision geometry and artist-authored topology without vertex quantization or welding. Generation proceeds as a coarse-to-fine cascade of two flow-matching models: an image-conditioned voxel flow first sketches the overall shape as a coarse occupancy scaffold, and a mesh flow then populates the scaffold with per-vertex latent tokens, conditioned on the image, the scaffold, and a requested vertex budget. This design delivers three practical capabilities: interactive generation speed through parallel flow-based synthesis; effective face-count control through the requested vertex budget; and native support for multi-part assets, whose components emerge directly from the generated connectivity. In our experiments, Meshy T2 achieves state-of-the-art geometric fidelity and completes end-to-end image-to-mesh generation within a median of 6 seconds, over an order of magnitude faster than autoregressive baselines. Code and weights will be available at https://github.com/meshy-dev/meshy-t2.