# From Design Draft to Real Attire: Unaligned Fashion Image Translation

arXiv: https://arxiv.org/abs/2008.01023 · HTML: https://mlsanity.com/paper/2008.01023/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks](https://mlsanity.com/paper/2407.01639/) (2024)
- [Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization](https://mlsanity.com/paper/2105.14739/) (2021)
- [fAshIon after fashion: A Report of AI in Fashion](https://mlsanity.com/paper/2105.03050/) (2021)
- [DiCTI: Diffusion-based Clothing Designer via Text-guided Input](https://mlsanity.com/paper/2407.03901/) (2024)
- [FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting](https://mlsanity.com/paper/2502.00992/) (2025)

## Abstract (arXiv)

Fashion manipulation has attracted growing interest due to its great application value, which inspires many researches towards fashion images. However, little attention has been paid to fashion design draft. In this paper, we study a new unaligned translation problem between design drafts and real fashion items, whose main challenge lies in the huge misalignment between the two modalities. We first collect paired design drafts and real fashion item images without pixel-wise alignment. To solve the misalignment problem, our main idea is to train a sampling network to adaptively adjust the input to an intermediate state with structure alignment to the output. Moreover, built upon the sampling network, we present design draft to real fashion item translation network (D2RNet), where two separate translation streams that focus on texture and shape, respectively, are combined tactfully to get both benefits. D2RNet is able to generate realistic garments with both texture and shape consistency to their design drafts. We show that this idea can be effectively applied to the reverse translation problem and present R2DNet accordingly. Extensive experiments on unaligned fashion design translation demonstrate the superiority of our method over state-of-the-art methods. Our project website is available at: https://victoriahy.github.io/MM2020/ .