Few-Part-Shot Font Generation

2025/09/12 by Akiba, Masaki, Takezaki, Shumpei, Haraguchi, Daichi +1
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2509.10006

Abstract

This paper proposes a novel model of few-part-shot font generation, which designs an entire font based on a set of partial design elements, i.e., partial shapes. Unlike conventional few-shot font generation, which requires entire character shapes for a couple of character classes, our approach only needs partial shapes as input. The proposed model not only improves the efficiency of font creation but also provides insights into how partial design details influence the entire structure of the individual characters.

Citations

• GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
• Font Style Interpolation with Diffusion Models
• Diff-Font: Diffusion Model for Robust One-Shot Font Generation
• Few-Shot Font Generation by Learning Fine-Grained Local Styles
• Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator
• Font Shape-to-Impression Translation
• Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
• Which Parts Determine the Impression of the Font?
• Few-shot Font Generation with Localized Style Representations and Factorization
• Denoising Diffusion Probabilistic Models
• Few-shot Compositional Font Generation with Dual Memory
• STEFANN: Scene Text Editor using Font Adaptive Neural Network
• Representation Learning with Contrastive Predictive Coding
• Separating Style and Content for Generalized Style Transfer
• Attention Is All You Need
• Deep Sets

Related

• Few-shot Font Generation with Weakly Supervised Localized Representations
• Few-shot Font Generation with Localized Style Representations and Factorization
• Few-Shot Font Generation by Learning Fine-Grained Local Styles
• Few-shot Font Generation by Learning Style Difference and Similarity
• Few shot font generation via transferring similarity guided global style and quantization local style