Multiple Style Transfer Via Variational Autoencoder

Modern works on style transfer focus on transferring style from a single image. Recently, some approaches study multiple style transfer; these, however, are either too slow or fail to mix multiple styles. We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, and it fuses different styles by linear interpolation and transfer the new style to the content image. To evaluate ST-VAE, we present experiments on COCO for single and multiple style transfer. Moreover, we present a case study revealing that ST-VAE outperforms other methods while being faster, flexible, and setting a new path for multiple style transfer. The code, models and results will be made available