“Unpaired Font Family Synthesis Using Conditional Generative Adversarial Networks”, 2021-10-11 (; similar):
Automatic font image synthesis has been an extremely active topic in recent years. Various deep learning-based approaches have been proposed to tackle this font synthesis task by considering it as an image-to-image translation problem in a supervised setting. However, all such approaches mainly focus on one-to-one font mapping, ie. synthesizing a single font style, making it difficult to handle more practical problems such as the font family synthesis, which is a one-to-many mapping problem. Moreover, this font family synthesis is more challenging because it is an unsupervised image-to-image translation problem, ie. no paired dataset is available during training.
To address this font family synthesis problem, we propose a method that uses a single generator to conditionally produce various font family styles to form a font family. To the best of our knowledge, our proposed method is the first to synthesize a font family (multiple font styles belonging to a font), instead of synthesizing a single font style. More specifically, our method is trained to learn a font family by conditioning on various styles, eg. normal, bold, italic, bold-italic, etc. After training, given an unobserved single font style (normal style font as an input), our method can successfully synthesize the remaining styles (eg. bold, italic, bold-italic, etc.) to complete the font family.
Qualitative and quantitative experiments were conducted to demonstrate the effectiveness of our proposed method.
[Keywords: font generation, Generative Adversarial Networks, style transfer, unsupervised image-to-image translation]