SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
This work solves the problem of realistic and customizable makeup application in photos for users in beauty and entertainment, though it is incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of makeup transfer and removal in facial images by addressing five key features simultaneously, which previous methods had not achieved, and demonstrates that their SLGAN model performs comparably or better than state-of-the-art methods.
There are five features to consider when using generative adversarial networks to apply makeup to photos of the human face. These features include (1) facial components, (2) interactive color adjustments, (3) makeup variations, (4) robustness to poses and expressions, and the (5) use of multiple reference images. Several related works have been proposed, mainly using generative adversarial networks (GAN). Unfortunately, none of them have addressed all five features simultaneously. This paper closes the gap with an innovative style- and latent-guided GAN (SLGAN). We provide a novel, perceptual makeup loss and a style-invariant decoder that can transfer makeup styles based on histogram matching to avoid the identity-shift problem. In our experiments, we show that our SLGAN is better than or comparable to state-of-the-art methods. Furthermore, we show that our proposal can interpolate facial makeup images to determine the unique features, compare existing methods, and help users find desirable makeup configurations.