CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator

TL;DR

This paper introduces CalliGAN, a novel Chinese calligraphy character generator that incorporates component information and improved embedding techniques to produce high-quality, style-aware characters, outperforming existing methods.

Contribution

The paper presents a new image-to-image translation model that integrates character component data and an enhanced embedding network for better Chinese calligraphy generation.

Findings

Generated characters are of higher quality than state-of-the-art methods.

Numerical evaluations show improved accuracy and style consistency.

Human studies confirm the visual appeal of the generated calligraphy.

Abstract

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.