Domain-Specific Mappings for Generative Adversarial Style Transfer
This work improves style transfer for image generation, but it is incremental as it builds on existing disentangled representation approaches.
The paper tackles the problem of style transfer by addressing the limitation of shared domain-invariant content spaces, which can compromise content representation, by introducing domain-specific mappings to remap latent features into domain-specific content spaces. Experiments show the method outperforms previous style transfer methods, particularly in challenging scenarios requiring semantic correspondences.
Style transfer generates an image whose content comes from one image and style from the other. Image-to-image translation approaches with disentangled representations have been shown effective for style transfer between two image categories. However, previous methods often assume a shared domain-invariant content space, which could compromise the content representation power. For addressing this issue, this paper leverages domain-specific mappings for remapping latent features in the shared content space to domain-specific content spaces. This way, images can be encoded more properly for style transfer. Experiments show that the proposed method outperforms previous style transfer methods, particularly on challenging scenarios that would require semantic correspondences between images. Code and results are available at https://acht7111020.github.io/DSMAP-demo/.