The Research and Implementation of Clothing Style Transfer Algorithm Based on CycleGAN

Abstract

The rapid development of artificial intelligence has brought about changes in many industries, and the application of deep learning technology in apparel design has become a current research hotspot. Since human subjective consciousness plays a dominant role in design style during the design process, artificial intelligence methods can effectively avoid the problem. In this paper, we focus on the application of Cycle Generative Adversarial Network (CycleGAN) in clothing style migration by giving an overview of CycleGAN. To address the problems exhibited by traditional generative adversarial networks in clothing style migration, this paper adds a filtering link before model training, which makes the generative adversarial network more focused and the edges more clear in the process of style migration. Through the comparison of experimental results, it is verified that the method works better in clothing style migration.