Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produce technically valid but overly fragmented atlases that lack semantic coherence. We introduce SeamGPT, an auto-regressive model that generates cutting seams by mimicking professional workflows. Our key technical innovation lies in formulating surface cutting as a next token prediction task: sample point clouds on mesh vertices and edges, encode them as shape conditions, and employ a GPT-style transformer to sequentially predict seam segments with quantized 3D coordinates. Our approach achieves exceptional performance on UV unwrapping benchmarks containing both manifold and non-manifold meshes, including artist-created, and 3D-scanned models. In addition, it enhances existing 3D segmentation tools by providing clean boundaries for part decomposition.
SeamGPT architecture: Point cloud encoder extracts shape context; Causal transformer decoder generates axis-ordered seam coordinates. Color indicates the prediction order is of the seam segments (red to blue).
@misc{seamgpt,
title={Auto-Regressive Surface Cutting},
author={Yang Li and Victor Cheung and Xinhai Liu and Yuguang Chen and Zhongjin Luo and Biwen Lei and Haohan Weng and Zibo Zhao and Jingwei Huang and Zhuo Chen and Chunchao Guo},
year={2025},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={},
}