Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
This addresses the challenge of creating diverse stylized Chinese characters with minimal examples, which is incremental as it builds on VAE methods for style transfer.
The paper tackles the problem of automatically generating stylized Chinese characters by proposing a Style-Aware Variational Auto-Encoder (SA-VAE) that disentangles content and style features, achieving one-shot/low-shot generalization to unseen styles.
Automatically writing stylized Chinese characters is an attractive yet challenging task due to its wide applicabilities. In this paper, we propose a novel framework named Style-Aware Variational Auto-Encoder (SA-VAE) to flexibly generate Chinese characters. Specifically, we propose to capture the different characteristics of a Chinese character by disentangling the latent features into content-related and style-related components. Considering of the complex shapes and structures, we incorporate the structure information as prior knowledge into our framework to guide the generation. Our framework shows a powerful one-shot/low-shot generalization ability by inferring the style component given a character with unseen style. To the best of our knowledge, this is the first attempt to learn to write new-style Chinese characters by observing only one or a few examples. Extensive experiments demonstrate its effectiveness in generating different stylized Chinese characters by fusing the feature vectors corresponding to different contents and styles, which is of significant importance in real-world applications.