论文标题
从设计草稿到真实服装：未对齐的时尚图像翻译
From Design Draft to Real Attire: Unaligned Fashion Image Translation
论文作者
论文摘要
由于其巨大的应用价值，时尚的操纵引起了人们日益增长的兴趣，这激发了许多研究时尚图像的研究。但是，对时装设计草案的关注很少。在本文中，我们研究了设计草案和真实时尚项目之间的一个新的非对齐翻译问题，其主要挑战在于两种方式之间的巨大未对准。我们首先收集成对的设计草稿和真实的时尚项目图像，而无需像素对齐。为了解决未对准问题，我们的主要思想是训练一个采样网络，以适应以结构对齐与输出的结构对齐的中间状态的输入。此外，在采样网络上，我们向真实的时尚项目翻译网络（D2RNET）介绍了设计草案，其中分别将重点放在纹理和形状上的两个单独的翻译流进行了巧妙的合并，以获得这两个好处。 D2Rnet能够生成具有质地和形状一致性的逼真的服装，以使其设计草稿。我们表明，这个想法可以有效地应用于反向翻译问题，并相应地呈现R2DNET。对未对准时装设计翻译的广泛实验证明了我们方法比最先进的方法的优越性。我们的项目网站可在以下网站上找到：https：//victoriahy.github.io/mm2020/。
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/ .
