Mesh seams play a pivotal role in partitioning 3D surfaces for UV parametrization and texture mapping. Poorly placed seams often result in severe UV distortion or excessive fragmentation, thereby hindering texture synthesis and disrupting artist workflows. Existing methods frequently trade one failure mode for another—producing either high distortion or many scattered islands. To address this, we introduce SeamCrafter, an autoregressive GPT-style seam generator conditioned on point cloud inputs. SeamCrafter employs a dual-branch point-cloud encoder that disentangles and captures complementary topological and geometric cues during pretraining. To further enhance seam quality, we fine-tune the model using Direct Preference Optimization (DPO) on a preference dataset derived from a novel seam-evaluation framework. This framework assesses seams primarily by UV distortion and fragmentation, and provides pairwise preference labels to guide optimization. Extensive experiments demonstrate that SeamCrafter produces seams with substantially lower distortion and fragmentation than prior approaches, while preserving topological consistency and visual fidelity.
SeamCrafter pipeline. An overview of SeamCrafter. The pipeline consists of three stages: (1) supervised pretraining with point clouds and ground-truth seam sequences; (2) candidate seam generation and quality assessment via our seam evaluation system to construct a preference dataset; and (3) post-training with Direct Preference Optimization (DPO) to refine the model.
@misc{xu2025seamcrafte,
title={SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning},
author={Duoteng Xu and Yuguang Chen and Jing Li and Xinhai Liu and Xueqi Ma and Zhuo Chen and Dongyu Zhang and Chunchao Guo},
year={2025},
eprint={2509.20725},
archivePrefix={arXiv},
primaryClass={cs.GR},
url={http://arxiv.org/abs/2509.20725},
}