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

TL;DR

DRG-Font introduces a contrastive, style-content disentanglement approach with dynamic reference selection for improved few-shot font generation, effectively capturing complex styles from limited exemplars.

Contribution

It proposes a novel contrastive learning framework with dynamic reference selection and multi-scale style-content decomposition for few-shot font generation.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively captures complex font styles from few references.

Demonstrates superior style consistency and content preservation.

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.