LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow

Hang Long^1,2,*   Tianhao Zhao^1,2,*   Junkai Lin^1,2   Youjia Zhang^1,2   Huipeng Guo¹
Rendong Liang²   Jiale Xu²   Jozef Hladký³   Matthias Nießner⁴   Yuanming Hu²   Wei Yang^1,†

¹Huazhong University of Science and Technology  ·  ²Meshy AI  ·  ³Independent Researcher  ·  ⁴Technical University of Munich

^*Equal contribution  ·  ^†Corresponding author

This work was completed during internships at Meshy AI.

Abstract

Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a joint latent space, entangling continuous vertex geometry with discrete combinatorial structure; this complicates flow learning and manifests as drifting vertices and broken surfaces. We present LATO.2, a factorized flow matching framework that decomposes mesh generation into a vertex flow followed by a connectivity flow conditioned on the realized vertices, with both stages anchored to a shared coarse voxel scaffold. Dedicated VAEs underpin the two stages, recovering vertices at sub-voxel precision and embedding discrete connectivity into a continuous latent space. We demonstrate two advantages unique to this factorization: (i) part-wise generation, in which the scaffold is partitioned and each part synthesized at full latent capacity, yielding substantially higher-resolution meshes than a monolithic latent permits; and (ii) topology-adaptive editing, in which manipulating first-stage vertices induces the corresponding connectivity without re-optimization. Experiments show that LATO.2 surpasses state-of-the-art topology-aware mesh generators in geometric fidelity and connectivity quality.