OutfitGAN: Learning Compatible Items for Generative Fashion Outfits

Maryam Moosaei, Yusan Lin, Ablaikhan Akhazhanov, Huiyuan Chen, Fei Wang, Hao Yang

CVPRW 2022 pp. 2272-2276

doi:10.1109/CVPRW56347.2022.00251 /cvprw/2022/moosaei2022cvprw-outfitgan/

Abstract

Fashion-on-demand is becoming an important concept for fashion industries. Many attempts have been made to leverage machine learning methods to generate fashion designs tailored to customers’ tastes. However, how to assemble items together (e.g., compatibility) is crucial in designing high-quality outfits for synthesis images. Here we propose a fashion generation model, named OutfitGAN, which contains two core modules: a Generative Adversarial Network and a Compatibility Network. The generative module is able to generate new realistic high quality fashion items from a specific category, while the compatibility network ensures reasonable compatibility among all items. The experimental results show the superiority of our OutfitGAN.

CVPRW Semantic Scholar

Cite

Text

Moosaei et al. "OutfitGAN: Learning Compatible Items for Generative Fashion Outfits." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00251

Markdown

[Moosaei et al. "OutfitGAN: Learning Compatible Items for Generative Fashion Outfits." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/moosaei2022cvprw-outfitgan/) doi:10.1109/CVPRW56347.2022.00251

BibTeX

@inproceedings{moosaei2022cvprw-outfitgan,
  title     = {{OutfitGAN: Learning Compatible Items for Generative Fashion Outfits}},
  author    = {Moosaei, Maryam and Lin, Yusan and Akhazhanov, Ablaikhan and Chen, Huiyuan and Wang, Fei and Yang, Hao},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {2272-2276},
  doi       = {10.1109/CVPRW56347.2022.00251},
  url       = {https://mlanthology.org/cvprw/2022/moosaei2022cvprw-outfitgan/}
}