A robust transformer GAN for unpaired data makeup transfer

The objective of makeup transfer is to apply the makeup style of, thereby creating the similar appearance as if it was professionally done. This technique has significant practical applications in fashion, beauty, and video special effects industries. However, there are several challenges faced by current makeup transfer models: (1) Low-resolution images can only achieve partial makeup transfer in mainstream models. (2) Difficulty arises in obtaining paired data consisting of both makeup and non-makeup images. (3) Spatial displacement occurs due to differences in subject and pose between reference and source images, affecting corresponding feature regions. (4) Mainstream models primarily focus on local feature characteristics while lacking global feature perception. To address these challenges, this paper proposes a nonpaired data makeup transfer model based on swin transformer generative adversarial networks. Additionally, an improved progressive generative adversarial network model (PSC-GAN), incorporating semantic perception and channel attention mechanisms, is proposed to enhance the effectiveness of makeup transfer.