DRG-Font : Dynamic Reference-Guided Few-shot Font Generation via Contrastive Style-Content Disentanglement

2026
Code (Coming Soon) arXiv
First research result visualization

Abstract

Few-shot Font Generation aims to generate stylistically consistent glyphs from a few reference glyphs. However, capturing complex font styles from a few exemplars remains challenging, and the existing methods often struggle to retain discernible local characteristics in generated samples. This paper introduces DRG-Font, a contrastive font generation strategy that learns complex glyph attributes by decomposing style and content embedding spaces. For optimal style supervision, the proposed architecture incorporates a Reference Selection (RS) Module to dynamically select the best style reference from an available pool of candidates. The network learns to decompose glyph attributes into style and shape priors through a Multi-scale Style Head Block (MSHB) and a Multi-scale Content Head Block (MCHB). For style adaptation, a Multi-Fusion Upsampling Block (MFUB) produces the target glyph by combining the reference style prior and target content prior. The proposed method demonstrates significant improvements over state-of-the-art approaches across multiple visual and analytical benchmarks.

BibTeX


      @misc{chakraborty2026drgfontdynamicreferenceguidedfewshot,
        title={DRG-Font: Dynamic Reference-Guided Few-shot Font Generation via Contrastive Style-Content Disentanglement},
        author={Rejoy Chakraborty and Prasun Roy and Saumik Bhattacharya and Umapada Pal},
        year={2026},
        eprint={2604.13797},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2604.13797}
      }