HiGAN: Handwriting Imitation Conditioned on Arbitrary-Length Texts and Disentangled Styles


  • Ji Gan University of Chinese Academy of Sciences
  • Weiqiang Wang University of Chinese Academy of Sciences




Neural Generative Models & Autoencoders


Given limited handwriting scripts, humans can easily visualize (or imagine) what the handwritten words/texts would look like with other arbitrary textual contents. Moreover, a person also is able to imitate the handwriting styles of provided reference samples. Humans can do such hallucinations, perhaps because they can learn to disentangle the calligraphic styles and textual contents from given handwriting scripts. However, computers cannot study to do such flexible handwriting imitation with existing techniques. In this paper, we propose a novel handwriting imitation generative adversarial network (HiGAN) to mimic such hallucinations. Specifically, HiGAN can generate variable-length handwritten words/texts conditioned on arbitrary textual contents, which are unconstrained to any predefined corpus or out-of-vocabulary words. Moreover, HiGAN can flexibly control the handwriting styles of synthetic images by disentangling calligraphic styles from the reference samples. Experiments on handwriting benchmarks validate our superiority in terms of visual quality and scalability when comparing to the state-of-the-art methods for handwritten word/text synthesis. The code and pre-trained models can be found at https://github.com/ganji15/HiGAN.




How to Cite

Gan, J., & Wang, W. (2021). HiGAN: Handwriting Imitation Conditioned on Arbitrary-Length Texts and Disentangled Styles. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 7484-7492. https://doi.org/10.1609/aaai.v35i9.16917



AAAI Technical Track on Machine Learning II