SE-GAN: Skeleton Enhanced GAN-based Model for Brush Handwriting Font Generation
This addresses the challenge of generating realistic brush handwriting fonts for designers and artists, representing an incremental advance in font generation by focusing on a previously understudied domain.
The paper tackles the problem of generating brush handwriting fonts, which involve complex strokes and structural changes, by proposing a GAN-based model that integrates skeleton information and uses a self-attentive refined attention module. The result is a competitive model demonstrated through quantitative and qualitative experiments on a new large-scale dataset of 15,000 high-resolution images across six styles.
Previous works on font generation mainly focus on the standard print fonts where character's shape is stable and strokes are clearly separated. There is rare research on brush handwriting font generation, which involves holistic structure changes and complex strokes transfer. To address this issue, we propose a novel GAN-based image translation model by integrating the skeleton information. We first extract the skeleton from training images, then design an image encoder and a skeleton encoder to extract corresponding features. A self-attentive refined attention module is devised to guide the model to learn distinctive features between different domains. A skeleton discriminator is involved to first synthesize the skeleton image from the generated image with a pre-trained generator, then to judge its realness to the target one. We also contribute a large-scale brush handwriting font image dataset with six styles and 15,000 high-resolution images. Both quantitative and qualitative experimental results demonstrate the competitiveness of our proposed model.