ResFFont: Few-Shot Font Generation based on Reversible Network

The technique of generating fonts with few-shot learning has become a popular research topic. The goal of this technique is to transform the source-to-target domain by using a small number of sample images to generate characters for new fonts. However, current research is limited by model frameworks and migration algorithms, which pose challenges for maintaining content integrity and stroke-level style consistency when generating Chinese characters. This paper proposes ResFFont, a reversible network-based model that uses a unique reversible framework and Global and Local Feature Fusion Module (GaLSFM) to ensure complete delivery of content information and stroke-level style consistency. The experimental results confirm the effectiveness and superiority of the ResFFont model, providing a new solution to the font generation problem.