A Unified Framework for Generalizable Style Transfer: Style and Content Separation

Abstract

Image style transfer has drawn broad attention in recent years. However, most existing methods aim to explicitly model the transformation between different styles, and the learned model is thus not generalizable to new styles. We here propose a unified style transfer framework for both character typeface transfer and neural style transfer tasks leveraging style and content separation. A key merit of such framework is its generalizability to new styles and contents. The overall framework consists of style encoder, content encoder, mixer and decoder. The style encoder and content encoder are used to extract the style and content representations from the corresponding reference images. The mixer integrates the above two representations and feeds it into the decoder to generate images with the target style and content. During training, the encoder networks learn to extract styles and contents from limited size of style/content reference images. This learning framework allows simultaneous style transfer among multiple styles and can be deemed as a special `multi-task' learning scenario. The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents. Under this framework, we design two individual networks for character typeface transfer and neural style transfer, respectively. For character typeface transfer, to separate the style features and content features, we leverage the conditional dependence of styles and contents given an image. For neural style transfer, we leverage the statistical information of feature maps in certain layers to represent style. Extensive experimental results have demonstrated the effectiveness and robustness of the proposed methods.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1711.06454

References in corpus (16)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Fully Convolutional Networks for Semantic Segmentation
• A Learned Representation For Artistic Style
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Unsupervised Image-to-Image Translation Networks
• Unsupervised Cross-Domain Image Generation
• Fast Patch-based Style Transfer of Arbitrary Style
• Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
• Demystifying Neural Style Transfer
• Understanding Deep Image Representations by Inverting Them
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
• Separating Style and Content for Generalized Style Transfer

Cited by in corpus (1)

• DLOW: Domain Flow for Adaptation and Generalization