Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator

TL;DR

This paper introduces CG-GAN, a component-aware font generation method that uses fine-grained supervision at the component level, significantly improving one-shot font synthesis and related tasks.

Contribution

It proposes a novel Component-Aware Module (CAM) for component-level supervision, enhancing font generation quality with a simpler generator architecture.

Findings

Outperforms state-of-the-art one-shot font generation methods

Effective in handwritten word synthesis and scene text editing

Demonstrates the importance of component-level supervision

Abstract

Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increases the difficulty to preserve local style patterns or detailed glyph structures. We investigate the drawbacks of previous studies and find that a coarse-grained discriminator is insufficient for supervising a font generator. To this end, we propose a novel Component-Aware Module (CAM), which supervises the generator to decouple content and style at a more fine-grained level, i.e., the component level. Different from previous studies struggling to increase the complexity of generators, we aim to perform more effective supervision for a relatively simple generator to achieve its full potential, which is a brand new perspective for font generation. The whole framework achieves remarkable results by coupling component-level supervision with adversarial learning, hence we call it Component-Guided GAN, shortly CG-GAN. Extensive experiments show that our approach outperforms state-of-the-art one-shot font generation methods. Furthermore, it can be applied to handwritten word synthesis and scene text image editing, suggesting the generalization of our approach.