Domain-Specific Mappings for Generative Adversarial Style Transfer
arXiv:2008.02198
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 (21)
- Auto-Encoding Variational Bayes
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution
- Toward Multimodal Image-to-Image Translation
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- Unsupervised Image-to-Image Translation Networks
- Texture Synthesis Using Convolutional Neural Networks
- U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
- Universal Style Transfer via Feature Transforms
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- InstaGAN: Instance-aware Image-to-Image Translation
- Learning Linear Transformations for Fast Arbitrary Style Transfer
- Deep Photo Style Transfer
- Few-Shot Unsupervised Image-to-Image Translation
- StyleBank: An Explicit Representation for Neural Image Style Transfer
- GANimation: Anatomically-aware Facial Animation from a Single Image
- Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
- ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
- 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