MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation

Jiale Xu, Wang Zhao, Ying Shan

Keywords: Autoregressive Mesh Generation, 3D Generation

TL;DR: An autoregressive mesh generation method that uses vertex-level tokenization and explicit sparse-voxel guidance.

Abstract: Autoregressive mesh generation has gained attention by tokenizing meshes into sequences and training models in a language‑modeling fashion. However, existing approaches suffer from two fundamental limitations: (i) low tokenization efficiency, which yields long sequences and prevents scaling to high‑poly meshes, and (ii) absence of geometry‑aware guidance, as generation is conditioned only on global shape embeddings rather than local surface cues. We introduce MeshWeaver, an autoregressive framework that treats mesh generation as a surface weaving process by directly predicting the next vertex instead of independent coordinates. At its core is a multi‑level sparse‑voxel encoder that injects geometric context into the generative process in three complementary ways: providing voxel features as vertex representations, guiding token prediction via cross‑attention to voxel features, and serving as a structural scaffold that constrains generation around the input surface. Our hierarchical design enables coarse‑to‑fine vertex prediction in a single decoding step, while tightly couples the generative model with 3D geometry. Extensive experiments demonstrate that MeshWeaver achieves a state‑of‑the‑art compression ratio of 18\%, can generates meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches.

Primary Area: generative models

Submission Number: 5178