SGCE-Font: Skeleton Guided Channel Expansion for Chinese Font Generation

TL;DR

This paper introduces SGCE-Font, a novel skeleton-guided channel expansion module that enhances Chinese font generation by integrating skeleton information, effectively alleviating mode collapse in GAN-based models and improving quality.

Contribution

The paper proposes the SGCE module that incorporates skeleton guidance into GANs for Chinese font generation, addressing mode collapse and boosting performance.

Findings

SGCE effectively alleviates mode collapse in CycleGAN.

CycleGAN with SGCE outperforms state-of-the-art models on key metrics.

SGCE can be integrated into various models as a plug-and-play module.

Abstract

The automatic generation of Chinese fonts is an important problem involved in many applications. The predominated methods for the Chinese font generation are based on the deep generative models, especially the generative adversarial networks (GANs). However, existing GAN-based methods (say, CycleGAN) for the Chinese font generation usually suffer from the mode collapse issue, mainly due to the lack of effective guidance information. This paper proposes a novel information guidance module called the skeleton guided channel expansion (SGCE) module for the Chinese font generation through integrating the skeleton information into the generator with the channel expansion way, motivated by the observation that the skeleton embodies both local and global structure information of Chinese characters. We conduct extensive experiments to show the effectiveness of the proposed module. Numerical results show that the mode collapse issue suffered by the known CycleGAN can be effectively alleviated by equipping with the proposed SGCE module, and the CycleGAN equipped with SGCE outperforms the state-of-the-art models in terms of four important evaluation metrics and visualization quality. Besides CycleGAN, we also show that the suggested SGCE module can be adapted to other models for Chinese font generation as a plug-and-play module to further improve their performance.