An Efficient Style Virtual Try on Network for Clothing Business Industry

TL;DR

This paper introduces a novel virtual try-on network that preserves clothing textures and patterns while allowing personalized style adjustments, improving realism and user experience in the clothing industry.

Contribution

The proposed network combines human parsing, UV mapping, and stylization to enhance virtual try-on accuracy and customization, addressing shape distortion issues in previous methods.

Findings

Retains clothing texture and pattern authenticity.

Enables real-time style customization.

Improves virtual try-on realism and user satisfaction.

Abstract

With the increasing development of garment manufacturing industry, the method of combining neural network with industry to reduce product redundancy has been paid more and more attention.In order to reduce garment redundancy and achieve personalized customization, more researchers have appeared in the field of virtual trying on.They try to transfer the target clothing to the reference figure, and then stylize the clothes to meet user's requirements for fashion.But the biggest problem of virtual try on is that the shape and motion blocking distort the clothes, causing the patterns and texture on the clothes to be impossible to restore. This paper proposed a new stylized virtual try on network, which can not only retain the authenticity of clothing texture and pattern, but also obtain the undifferentiated stylized try on. The network is divided into three sub-networks, the first is the user image, the front of the target clothing image, the semantic segmentation image and the posture heat map to generate a more detailed human parsing map. Second, UV position map and dense correspondence are used to map patterns and textures to the deformed silhouettes in real time, so that they can be retained in real time, and the rationality of spatial structure can be guaranteed on the basis of improving the authenticity of images. Third,Stylize and adjust the generated virtual try on image. Through the most subtle changes, users can choose the texture, color and style of clothing to improve the user's experience.