Efficient and Scalable Chinese Vector Font Generation via Component Composition
This addresses the problem of scalable font generation for Chinese typography, which is incremental as it builds on existing component-based ideas but applies them innovatively to vector fonts.
The paper tackles the challenge of generating Chinese vector fonts for numerous complex characters by proposing an efficient and scalable approach based on component composition, resulting in significant improvements over state-of-the-art methods in generating large-scale characters and zero-shot font extension.
Chinese vector font generation is challenging due to the complex structure and huge amount of Chinese characters. Recent advances remain limited to generating a small set of characters with simple structure. In this work, we first observe that most Chinese characters can be disassembled into frequently-reused components. Therefore, we introduce the first efficient and scalable Chinese vector font generation approach via component composition, allowing generating numerous vector characters from a small set of components. To achieve this, we collect a large-scale dataset that contains over \textit{90K} Chinese characters with their components and layout information. Upon the dataset, we propose a simple yet effective framework based on spatial transformer networks (STN) and multiple losses tailored to font characteristics to learn the affine transformation of the components, which can be directly applied to the Bézier curves, resulting in Chinese characters in vector format. Our qualitative and quantitative experiments have demonstrated that our method significantly surpasses the state-of-the-art vector font generation methods in generating large-scale complex Chinese characters in both font generation and zero-shot font extension.