From Design Draft to Real Attire: Unaligned Fashion Image Translation
This work addresses a specific problem in fashion image translation for designers and applications, but it is incremental as it builds on existing translation methods with a novel adaptation for unaligned data.
The paper tackles the problem of translating unaligned fashion design drafts into realistic garment images, addressing the challenge of structural misalignment between the two modalities. It introduces D2RNet, which uses a sampling network for alignment and separate streams for texture and shape, achieving superior results over state-of-the-art methods in experiments.
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/ .