MeshFlow: 基于等变流匹配的网格生成
MeshFlow: Mesh Generation with Equivariant Flow Matching
AI总结：
提出MeshFlow，利用等变最优传输流匹配模型直接生成三角网格，避免序列化，通过改进扩散变压器架构实现等变性，推理速度提升约18倍。
摘要：
网格是最常见的3D场景表示之一，但直接生成网格具有挑战性，因为该表示包含重要的对称性，包括面和顶点的排列不变性。MeshFlow学习直接生成三角网格作为三角汤，避免将网格序列化为长的自回归序列。我们采用等变最优传输流匹配模型，尊重三角汤的关键对称性：面的任意排列和每个面内顶点的排列。为此，我们提出了一种简单而有效的扩散变压器架构修改，得到一个可扩展的网络，能够在保持所需等变性的同时建模速度场。我们进一步引入基于最优传输的训练目标，通过消除违反这些对称性的监督信号来改善收敛。MeshFlow实现了与最先进的自回归网格生成器相当的网格质量，同时在推理时提供约18倍的加速。项目页面见此https URL。
英文摘要：
Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permutation invariance of faces and vertices. MeshFlow learns to generate triangle meshes directly as triangle soups, avoiding the need to serialize meshes into long autoregressive sequences. We adopt equivariant optimal-transport flow matching models that respect the key symmetries of triangle soups: arbitrary permutations of faces and permutations of the vertices within each face. Toward this goal, we propose a simple yet effective modification to the Diffusion Transformer architecture, resulting in a scalable network capable of modeling a velocity field while maintaining the desired equivariance. We further introduce an optimal-transport-based training objective that improves convergence by eliminating supervision signals that violate these symmetries. MeshFlow achieves mesh quality comparable to state-of-the-art autoregressive mesh generators while providing about an 18$\times$ speedup during inference. Project page is at https://qiisun.github.io/MeshFlow/.
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。
