English

Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern Generation

Computer Vision and Pattern Recognition 2026-03-18 v1

Abstract

Textile pattern generation (TPG) aims to synthesize fine-grained textile pattern images based on given clothing images. Although previous studies have not explicitly investigated TPG, existing image-to-image models appear to be natural candidates for this task. However, when applied directly, these methods often produce unfaithful results, failing to preserve fine-grained details due to feature confusion between complex textile patterns and the inherent non-rigid texture distortions in clothing images. In this paper, we propose a novel method, SLDDM-TPG, for faithful and high-fidelity TPG. Our method consists of two stages: (1) a latent disentangled network (LDN) that resolves feature confusion in clothing representations and constructs a multi-dimensional, independent clothing feature space; and (2) a semi-supervised latent diffusion model (S-LDM), which receives guidance signals from LDN and generates faithful results through semi-supervised diffusion training, combined with our designed fine-grained alignment strategy. Extensive evaluations show that SLDDM-TPG reduces FID by 4.1 and improves SSIM by up to 0.116 on our CTP-HD dataset, and also demonstrate good generalization on the VITON-HD dataset.

Keywords

Cite

@article{arxiv.2603.16747,
  title  = {Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern Generation},
  author = {Chenggong Hu and Yi Wang and Mengqi Xue and Haofei Zhang and Jie Song and Li Sun},
  journal= {arXiv preprint arXiv:2603.16747},
  year   = {2026}
}

Comments

9 pages, 7 figures, acceptted by AAAI2026, the code is available at https://github.com/Cg-Hu/SLDDM-TPG

R2 v1 2026-07-01T11:24:33.128Z