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

TL;DR

This paper introduces a unified, generalizable framework for style transfer that separates style and content representations, enabling effective transfer across multiple styles and contents in both character typeface and neural style transfer tasks.

Contribution

The paper proposes a novel unified framework that generalizes style transfer to new styles and contents by separating style and content representations, applicable to multiple tasks.

Findings

Framework achieves effective style transfer across multiple styles.

Models demonstrate robustness and generalizability to new styles.

Experimental results validate the effectiveness of the proposed methods.

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.