Paper 2604.09132
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
- Published
- Apr 2026
- Research lab
- Independent
- Citations
- 2
- GitHub
- 181 stars
01 In brief
Summary
The paper introduces Strips as Tokens (SATO), a framework for generating artist-quality 3D meshes with native UV segmentation using autoregressive transformers.
SATO uses a strip-based tokenization strategy that serializes meshes as connected chains of faces, preserving edge flow and structural regularity.
This unified representation allows the same token sequence to be decoded as either triangle or quadrilateral meshes, enabling joint training on both data types.
The method also extends the token vocabulary with segmentation tokens to encode UV island boundaries directly in the sequence.
SATO employs a three-stage training pipeline: large-scale triangle mesh pretraining, UV segmentation post-training, and quad mesh fine-tuning.
Experiments show SATO consistently outperforms prior methods (MeshAnythingV2, TreeMeshGPT, BPT, DeepMesh) in geometric quality, structural coherence, and UV segmentation across ShapeNet, Thingi10K, and Objaverse datasets.
User studies confirm artist preference for SATO outputs.
The framework supports generation from point clouds, images, and text prompts, and demonstrates diversity in outputs.
Limitations include occasional degenerate faces in quad decoding and quality bounded by available quad-mesh datasets.
02 From the paper
Abstract
Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes. A key advantage of this formulation is its unified representation, enabling the same token sequence to be decoded into either a triangle or quadrilateral mesh. This flexibility facilitates joint training on both data types: large-scale triangle data provides fundamental structural priors, while high-quality quad data enhances the geometric regularity of the outputs. Extensive experiments demonstrate that SATO consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation. Project page: https://ruixu.me/html/SATO/index.html