MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
2026-06-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce MeshWeaver, a new way to create 3D mesh shapes by predicting how the surface is woven together instead of guessing points independently. Their method uses a special 3D grid to understand local surface details, helping the model generate more accurate and detailed shapes. This approach also compresses data better and can handle more complex meshes than previous methods. Overall, the authors show that MeshWeaver produces high-quality 3D shapes more efficiently.
autoregressive generation3D meshtokenizationsparse voxel encodercross-attentiongeometry-aware guidancevertex predictioncompression ratiocoarse-to-fine decodingsurface weaving
Authors
Jiale Xu, Wang Zhao, Ying Shan
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 token 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 coupling the generative model with 3D geometry. Extensive experiments demonstrate that MeshWeaver achieves a state-of-the-art compression ratio of 18%, can generate meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches.