SE-GAN: Skeleton Enhanced GAN-based Model for Brush Handwriting Font Generation

TL;DR

This paper introduces SE-GAN, a novel GAN-based model that incorporates skeleton information for generating realistic brush handwriting fonts, addressing the complexity of strokes and structure changes.

Contribution

The paper presents a new skeleton-enhanced GAN model and a large-scale dataset for brush handwriting font generation, improving realism and diversity.

Findings

The model outperforms existing methods in quality and diversity.

Skeleton information significantly improves font realism.

The dataset supports future research in handwriting font generation.

Abstract

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.