ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach

TL;DR

ZiGAN is an end-to-end framework for fine-grained Chinese calligraphy font generation that effectively transfers styles with few reference samples, avoiding complex preprocessing and manual operations.

Contribution

It introduces a novel few-shot style transfer method for Chinese calligraphy fonts that requires no manual preprocessing or extensive reference data.

Findings

Achieves state-of-the-art results in few-shot Chinese style transfer.

Requires only a few paired samples for style transfer.

Demonstrates strong generalization ability across styles.

Abstract

Chinese character style transfer is a very challenging problem because of the complexity of the glyph shapes or underlying structures and large numbers of existed characters, when comparing with English letters. Moreover, the handwriting of calligraphy masters has a more irregular stroke and is difficult to obtain in real-world scenarios. Recently, several GAN-based methods have been proposed for font synthesis, but some of them require numerous reference data and the other part of them have cumbersome preprocessing steps to divide the character into different parts to be learned and transferred separately. In this paper, we propose a simple but powerful end-to-end Chinese calligraphy font generation framework ZiGAN, which does not require any manual operation or redundant preprocessing to generate fine-grained target-style characters with few-shot references. To be specific, a few paired samples from different character styles are leveraged to attain a fine-grained correlation between structures underlying different glyphs. To capture valuable style knowledge in target and strengthen the coarse-grained understanding of character content, we utilize multiple unpaired samples to align the feature distributions belonging to different character styles. By doing so, only a few target Chinese calligraphy characters are needed to generated expected style transferred characters. Experiments demonstrate that our method has a state-of-the-art generalization ability in few-shot Chinese character style transfer.