CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator
This addresses the problem of generating stylized Chinese characters for art and design applications, but it is incremental as it builds on existing image-to-image translation approaches.
The paper tackled generating Chinese calligraphy characters by incorporating component information and an improved network for embedding conversion, resulting in high-quality outputs that outperformed state-of-the-art methods in numerical and human evaluations.
Chinese calligraphy is the writing of Chinese characters as an art form performed with brushes so Chinese characters are rich of shapes and details. Recent studies show that Chinese characters can be generated through image-to-image translation for multiple styles using a single model. We propose a novel method of this approach by incorporating Chinese characters' component information into its model. We also propose an improved network to convert characters to their embedding space. Experiments show that the proposed method generates high-quality Chinese calligraphy characters over state-of-the-art methods measured through numerical evaluations and human subject studies.