Multi-Content GAN for Few-Shot Font Style Transfer
This addresses the challenge of font style transfer for applications like movie posters or infographics, but it is incremental as it builds on existing GAN methods.
The paper tackles the problem of generating unobserved glyphs in highly-stylized fonts from very few examples, achieving effective generalization with a stacked conditional GAN model that transfers style to unseen contents.
In this work, we focus on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface. To generate a set of multi-content images following a consistent style from very few examples, we propose an end-to-end stacked conditional GAN model considering content along channels and style along network layers. Our proposed network transfers the style of given glyphs to the contents of unseen ones, capturing highly stylized fonts found in the real-world such as those on movie posters or infographics. We seek to transfer both the typographic stylization (ex. serifs and ears) as well as the textual stylization (ex. color gradients and effects.) We base our experiments on our collected data set including 10,000 fonts with different styles and demonstrate effective generalization from a very small number of observed glyphs.