GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks - Hayashi - 2019

 

Info

  • Title: GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
  • Task: Font Generation
  • Author: H. Hayashi, K. Abe, and S. Uchida
  • Date: May 2019
  • Arxiv: 1905.12502

Highlights & Drawbacks

  • Two encode vectors for character and style, respectively

Motivation & Design

The main frame work is a DCGAN, with Wasserstein distance as discriminator Loss. Notice that char-ID is encoded with a saperate one-hot vector as priors applied to random vector for generator. GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks

Performance & Ablation Study

legibility evaluation

GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks

Style Consistency

The metric of style consistency is defined as: Cs=1NCn=1N1d¯nc=1C(dn,cd¯n)2, where N is the number of generated images (we used N=10,000 in this experiment), C is the number of character classes, i.e.,C=26, dn,c is the distance between the generated font and the nearest real font, and d¯is the average of dn,c over c. The metric C is the averaged coefficient of variation of dn,c, and represents an intra-style variation of the generated font images. The lower Cs is, the higher style consistency is.

GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks