MeshRipple: Structured Autoregressive Generation of Artist-Meshes
Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, Jiayi Yang, Tianle Guo, Yang Yang, Jianwen Li
Abstract
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.
BibTeX
@inproceedings{cvpr2026_meshripplestruct,
title = {MeshRipple: Structured Autoregressive Generation of Artist-Meshes},
author = {Junkai Lin and Hang Long and Huipeng Guo and Jielei Zhang and Jiayi Yang and Tianle Guo and Yang Yang and Jianwen Li and Wenxiao ZHANG and Matthias Nießner and Wei Yang},
booktitle = {CVPR 2026},
year = {2026}
}