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

2026-04-15

AI Summary

This work addresses the challenge of accurately modeling complex typographic styles and preserving fine local details in few-shot font generation from limited reference glyphs. To this end, the authors propose a contrastive learning–based framework that explicitly disentangles style and content representations. The approach incorporates a dynamic reference selection mechanism to adaptively identify the most informative reference glyphs, along with multi-scale style and content priors. Key components include a Reference Selection (RS) module, Multi-Scale Style and Content Head Blocks (MSHB/MCHB), and a Multi-Fusion Upsampling Block (MFUB), which collectively enhance both style consistency and structural fidelity in the generated characters. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art approaches across multiple visual and quantitative evaluation metrics.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Few-shot Font Generation
• Style-Content Disentanglement
• Font Style Consistency
• Local Characteristic Preservation

Innovation

• contrastive disentanglement
• few-shot font generation
• dynamic reference selection
• multi-scale feature extraction
• style-content fusion