用结构化隐变量实现高效3D网格生成，保持拓扑不变性。
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
- 将网格表示为表面锚定的顶点位移场，用稀疏体素VAE压缩为拓扑感知隐空间
- 通过逐步细分与剪枝体素隐变量，精准定位顶点并直接预测边连接关系
- 无需等值面提取或启发式拼接，适合复杂几何与高效推理场景
本文提出LAT0，一种新型拓扑保持的隐表示，支持基于流匹配的显式3D网格可扩展生成。LAT0将网格表示为锚定在表面的顶点位移场（VDF），采用稀疏体素变分自编码器（VAE）将其显式信号压缩为结构化、拓扑感知的体素隐变量。解码时，VAE逐步细分并剪枝隐体素以精确定位顶点；专用连接头直接从体素隐变量预测顶点对之间的边连接，无需等值面提取或启发式网格化即可恢复拓扑。在生成建模中，LAT0采用两阶段流匹配：先合成结构体素，再细化体素级拓扑特征。相比以往基于等值面或三角形的扩散模型及自回归生成方法，LAT0在保持复杂几何与良好拓扑的同时，具备更高的推理效率。
原文摘要 · Abstract (English)
In this paper, we introduce LATO, a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes. LATO represents a mesh as a Vertex Displacement Field (VDF) anchored on surface, incorporating a sparse voxel Variational Autoencoder (VAE) to compress this explicit signal into a structured, topology-aware voxel latent. To decapsulate the mesh, the VAE decoder progressively subdivides and prunes latent voxels to instantiate precise vertex locations. In the end, a dedicated connection head queries the voxel latent to predict edge connectivity between vertex pairs directly, allowing mesh topology to be recovered without isosurface extraction or heuristic meshing. For generative modeling, LATO adopts a two-stage flow matching process, first synthesizing the structure voxels and subsequently refining the voxel-wise topology features. Compared to prior isosurface/triangle-based diffusion models and autoregressive generation approaches, LATO generates meshes with complex geometry, well-formed topology while being highly efficient in inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。