Attribute editing has become an important and emerging topic of computer vision. In this paper, we consider a task: given a reference garment image A and another image B with target attribute (collar/sleeve), generate a photo-realistic image which combines the texture from reference A and the new attribute from reference B. The highly convoluted attributes and the lack of paired data are the main challenges to the task. To overcome those limitations, we propose a novel self-supervised model to synthesize garment images with disentangled attributes (e.g., collar and sleeves) without paired data. Our method consists of a reconstruction learning step and an adversarial learning step. The model learns texture and location information through reconstruction learning. And, the model's capability is generalized to achieve single-attribute manipulation by adversarial learning. Meanwhile, we compose a new dataset, named GarmentSet, with annotation of landmarks of collars and sleeves on clean garment images. Extensive experiments on this dataset and real-world samples demonstrate that our method can synthesize much better results than the state-of-the-art methods in both quantitative and qualitative comparisons.
@article{arxiv.2001.06427,
title = {TailorGAN: Making User-Defined Fashion Designs},
author = {Lele Chen and Justin Tian and Guo Li and Cheng-Haw Wu and Erh-Kan King and Kuan-Ting Chen and Shao-Hang Hsieh and Chenliang Xu},
journal= {arXiv preprint arXiv:2001.06427},
year = {2020}
}