| dc.description.abstract | The vigorous development of online shopping drives the transformation of physical stores. The physical stores actively develop online sales platforms in order to increase their sales on electronic sales channels. Therefore, we want to provide more product information to consumers. With the information, we can stimulate customers’ desire for the products. Then customers buy it. Clothing is one of the main products sold in online shopping. Therefore, various clothing stores have launched virtual try-on system. Consumers do not need to try on the clothes in person, and they can have a reference for the clothes.
Computer vision technology is an important part of virtual try-on system. Generative Adversarial Network has been widely used in this field. In this paper, we adopt three Spectral Normalized Generative Adversarial Networks and Openpose for human body keypoints detection. The three Spectral Normalized Generative Adversarial Networks was used respectively to generate the arms of target person, the warping clothes, and the final try-on result. We will call it visual try-on because of it only depends on image. The proposed method is composed of three modules, including semantic generation module, clothing warping module, and content fusion module. The clothes details are retained through the spatial transformer network. We hope to make the generated results as close as to the reality. This paper only try-on the upper clothing. We compare clothes and hands separately, with different loss functions. In the future, the methods mentioned in this paper can also be applied to various other types of experiments, such as hair styling, lower clothing try-on, clothing design simulation.
Keywords: Generative Adversarial Network(GAN), spectral normalized Generative Adversarial Networks(SNGAN), virtual try-on, visual try-on, Openpose | en_US |