Neural Style Difference Transfer and Its Application to Font Generation
This addresses the problem of manual font creation for designers and typographers, though it appears incremental as it builds on existing neural style transfer techniques.
The paper tackles the time-consuming and skill-intensive process of font design by introducing a method to automatically generate fonts using neural style transfer, where font style differences between fonts are identified and transferred to create new fonts.
Designing fonts requires a great deal of time and effort. It requires professional skills, such as sketching, vectorizing, and image editing. Additionally, each letter has to be designed individually. In this paper, we will introduce a method to create fonts automatically. In our proposed method, the difference of font styles between two different fonts is found and transferred to another font using neural style transfer. Neural style transfer is a method of stylizing the contents of an image with the styles of another image. We proposed a novel neural style difference and content difference loss for the neural style transfer. With these losses, new fonts can be generated by adding or removing font styles from a font. We provided experimental results with various combinations of input fonts and discussed limitations and future development for the proposed method.