MeshFlow：基于 MeshVAE 与流式扩散 Transformer 的高效艺术网格生成
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer
用带对比损失的 VAE 把连续顶点坐标与离散连接关系压进一个紧凑的连续潜空间，再用 Rectified-Flow Transformer 并行生成全部顶点与边，为三维网格生成提供了可替代自回归 token 预测的潜空间+流匹配范式。
原文依据 a Variational Autoencoder (VAE) that, supervised with a contrastive loss, represents both continuous vertex positions and discrete connectivity in a continuous latent space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 MeshFlow，一种用于压缩并生成类艺术家风格三维网格的新方法。当前的网格生成器常采用自回归（AR）下一 token 预测，鉴于网格连接关系的离散性，这是一个自然的选择，但其推理开销随网格规模呈二次增长，因而扩展性很差。自回归方法还需要对顶点坐标做离散化，这会引入量化误差并可能导致顶点坍缩。为应对这些挑战，我们引入一个变分自编码器（VAE），在对比损失的监督下，将连续的顶点位置与离散的连接关系表示在一个连续潜空间中。该潜空间比此前基于 token 的网格表示紧凑得多。随后我们构建了一个基于 Rectified-Flow Transformer 的三维生成器，并行地生成全部网格顶点与边。该模型采样网格的速度比最快的自回归生成器快 26 倍，同时在标准网格生成指标上达到最优精度。
英文原文摘要 1034 字符
We present MeshFlow, a new method for compressing and generating artist-like 3D meshes. Current mesh generators often adopt Auto-Regressive (AR) next-token prediction, a natural choice given the discrete nature of mesh connectivity, which, however, scales poorly due to the inference cost being quadratic in mesh size. AR methods also require discretizing the vertex coordinates, which introduces quantization errors and can cause vertex collapse. To address these challenges, we introduce a Variational Autoencoder (VAE) that, supervised with a contrastive loss, represents both continuous vertex positions and discrete connectivity in a continuous latent space.This latent space is significantly more compact than prior token-based mesh representations. We then build a 3D generator based on a Rectified-Flow transformer, which generates all mesh vertices and edges in parallel. This model samples meshes 26xfaster than the fastest AR generator while also achieving state-of-the-art accuracy across standard mesh-generation metrics.