An Attribute-enhanced Method based on Latent Space Factorization for Face Image Style Transfer

Abstract

In recent years, arbitrary style transfer (AST) with high quality develops rapidly and the application is widespread. Customers desire to stylize their portraits and edit face attributes simultaneously. To satisfy people's demands, we design a whole framework to complete both global style transfer in color and local style transfer in attributes. First, a target attribute enhancement module guided by the latent space factorization is presented to alleviate over-editing problems and obtain style codes. Then, a local-global fusion module is proposed to integrate target style codes and global features. Besides, a contrastive coherence preserving loss is built in a pre-trained style transfer network to better adapt to face images. The experiments show that our model can generate pleasant images.