StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding


  • Jinshan Zeng Jiangxi Normal University
  • Qi Chen Jiangxi Normal University
  • Yunxin Liu Jiangxi Normal University
  • Mingwen Wang Jiangxi Normal University
  • Yuan Yao Hong Kong University of Science and Technology





The generation of stylish Chinese fonts is an important problem involved in many applications. Most of existing generation methods are based on the deep generative models, particularly, the generative adversarial networks (GAN) based models. However, these deep generative models may suffer from the mode collapse issue, which significantly degrades the diversity and quality of generated results. In this paper, we introduce a one-bit stroke encoding to capture the key mode information of Chinese characters and then incorporate it into CycleGAN, a popular deep generative model for Chinese font generation. As a result we propose an efficient method called StrokeGAN, mainly motivated by the observation that the stroke encoding contains amount of mode information of Chinese characters. In order to reconstruct the one-bit stroke encoding of the associated generated characters, we introduce a stroke-encoding reconstruction loss imposed on the discriminator. Equipped with such one-bit stroke encoding and stroke-encoding reconstruction loss, the mode collapse issue of CycleGAN can be significantly alleviated, with an improved preservation of strokes and diversity of generated characters. The effectiveness of StrokeGAN is demonstrated by a series of generation tasks over nine datasets with different fonts. The numerical results demonstrate that StrokeGAN generally outperforms the state-of-the-art methods in terms of content and recognition accuracies, as well as certain stroke error, and also generates more realistic characters.




How to Cite

Zeng, J., Chen, Q., Liu, Y., Wang, M., & Yao, Y. (2021). StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3270-3277.



AAAI Technical Track on Computer Vision III