# TailorGAN: Making User-Defined Fashion Designs

arXiv: https://arxiv.org/abs/2001.06427 · HTML: https://mlsanity.com/paper/2001.06427/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2020.

## Built on by (most cited first, 6 of 6)

- [PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns](https://mlsanity.com/paper/2312.04534/) (2023)
- [FashionTex: Controllable Virtual Try-on with Text and Texture](https://mlsanity.com/paper/2305.04451/) (2023)
- [HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models](https://mlsanity.com/paper/2401.07450/) (2024)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [fAshIon after fashion: A Report of AI in Fashion](https://mlsanity.com/paper/2105.03050/) (2021)
- [Fashion Object Detection for Tops & Bottoms](https://mlsanity.com/paper/2305.18482/) (2023)

## Abstract (arXiv)

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.