W-Net: One-Shot Arbitrary-Style Chinese Character Generation with Deep Neural Networks

TL;DR

This paper introduces W-Net, a deep learning framework capable of generating Chinese characters in arbitrary styles from a single example, addressing the complexity of Chinese script variations.

Contribution

The paper presents a novel one-shot style transfer model for Chinese characters, enabling arbitrary style generation with a single reference character.

Findings

W-Net outperforms existing methods in one-shot Chinese character style generation.

The model effectively captures style from a single character and applies it to generate diverse characters.

Experimental results demonstrate significant improvements over competitive approaches.

Abstract

Due to the huge category number, the sophisticated combinations of various strokes and radicals, and the free writing or printing styles, generating Chinese characters with diverse styles is always considered as a difficult task. In this paper, an efficient and generalized deep framework, namely, the W-Net, is introduced for the one-shot arbitrary-style Chinese character generation task. Specifically, given a single character (one-shot) with a specific style (e.g., a printed font or hand-writing style), the proposed W-Net model is capable of learning and generating any arbitrary characters sharing the style similar to the given single character. Such appealing property was rarely seen in the literature. We have compared the proposed W-Net framework to many other competitive methods. Experimental results showed the proposed method is significantly superior in the one-shot setting.