论文标题
LGVTON：具有里程碑意义的指导方法虚拟试验
LGVTON: A Landmark Guided Approach to Virtual Try-On
论文作者
论文摘要
在本文中，我们提出了一个具有里程碑意义的指导性化衣服的指导性化合物方法，该方法旨在解决电子商务网站上的服装试验问题。鉴于两个人的图像：一个人和模特，它会产生穿着模特衣服的人的演绎。考虑到大多数电子商务网站上通常不可用的是仅可用的大多数电子商务网站图像，这是有用的。我们遵循三阶段的方法来实现我们的目标。在第一阶段，LGVTON使用基于薄板样条（TPS）转换来扭曲模型的衣服以适合该人。与以前的基于TPS的方法不同，我们使用（人类和衣服的）地标来计算TPS转换。这使扭曲能够独立于衣服上存在的复杂图案，例如条纹，花卉和纹理。但是，此计算的翘曲可能并不总是很精确。因此，我们借助蒙版生成器（阶段2）和图像合成器（阶段3）模块进一步完善了它。面膜发电机改善了扭曲的衣服的配合，图像合成器可确保逼真的输出。为了解决缺乏配对培训数据的问题，我们采取了自我监督的培训策略。在这里，配对数据是指型号的图像对和穿着相同布的人。我们将LGVTON与两个流行的时尚数据集上的四种现有方法进行了比较，即MPV，并使用两种性能措施（FID（FréchetInception距离））和SSIM（结构相似性指数）进行了比较。在大多数情况下，提出的方法的表现优于最新方法。
In this paper, we propose a Landmark Guided Virtual Try-On (LGVTON) method for clothes, which aims to solve the problem of clothing trials on e-commerce websites. Given the images of two people: a person and a model, it generates a rendition of the person wearing the clothes of the model. This is useful considering the fact that on most e-commerce websites images of only clothes are not usually available. We follow a three-stage approach to achieve our objective. In the first stage, LGVTON warps the clothes of the model using a Thin-Plate Spline (TPS) based transformation to fit the person. Unlike previous TPS-based methods, we use the landmarks (of human and clothes) to compute the TPS transformation. This enables the warping to work independently of the complex patterns, such as stripes, florals, and textures, present on the clothes. However, this computed warp may not always be very precise. We, therefore, further refine it in the subsequent stages with the help of a mask generator (Stage 2) and an image synthesizer (Stage 3) modules. The mask generator improves the fit of the warped clothes, and the image synthesizer ensures a realistic output. To tackle the problem of lack of paired training data, we resort to a self-supervised training strategy. Here paired data refers to the image pair of model and person wearing the same cloth. We compare LGVTON with four existing methods on two popular fashion datasets namely MPV and DeepFashion using two performance measures, FID (Fréchet Inception Distance) and SSIM (Structural Similarity Index). The proposed method in most cases outperforms the state-of-the-art methods.
