Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

2026-04-10

AI Summary

Existing autoregressive methods for 3D mesh generation struggle to meet artists’ demands for continuous edge flow, structural regularity, and efficient UV segmentation. This work proposes a novel token ordering strategy inspired by triangle strips, representing meshes as connected face chains that explicitly encode UV boundaries. For the first time within an autoregressive Transformer framework, this approach unifies the flexible decoding of both triangular and quadrilateral meshes and leverages joint training on both mesh types to enhance generation quality. The method inherently preserves artist-preferred edge flow and semantic layout, significantly outperforming existing techniques in geometric fidelity, structural consistency, and UV segmentation—thereby aligning more closely with professional creation standards.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• mesh generation
• token ordering
• artist-quality modeling
• UV segmentation
• structural regularity

Innovation

• triangle strips
• token ordering
• UV segmentation
• unified mesh representation
• autoregressive generation