AI RESEARCH
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer
arXiv CS.CV
•
ArXi:2606.04621v1 Announce Type: new We present MeshFlow, a new method for 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 topology. However, AR methods scale poorly because the inference cost is quadratic in mesh size. They also require discretizing the vertex coordinates, which