SVG Vector Font Generation for Chinese Characters with Transformer
This addresses the labor-intensive task of font design for Chinese characters, which has high demand but was previously unsolved due to complexity, representing a significant advancement in automated font generation.
The study tackled the problem of automatically generating Chinese vector fonts from a single style and content reference, achieving the first successful generation of Chinese vector fonts using a novel Transformer-based network architecture, though limited to the sans-serif family.
Designing fonts for Chinese characters is highly labor-intensive and time-consuming. While the latest methods successfully generate the English alphabet vector font, despite the high demand for automatic font generation, Chinese vector font generation has been an unsolved problem owing to its complex shape and numerous characters. This study addressed the problem of automatically generating Chinese vector fonts from only a single style and content reference. We proposed a novel network architecture with Transformer and loss functions to capture structural features without differentiable rendering. Although the dataset range was still limited to the sans-serif family, we successfully generated the Chinese vector font for the first time using the proposed method.