Domain-Specific Mappings for Generative Adversarial Style Transfer

Abstract

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/.

ECCV 2020, Project url: https://acht7111020.github.io/DSMAP-demo/

References in corpus (6)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• InstaGAN: Instance-aware Image-to-Image Translation
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
• Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation