English

Few-Part-Shot Font Generation

Computer Vision and Pattern Recognition 2025-09-15 v1

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.

Cite

@article{arxiv.2509.10006,
  title  = {Few-Part-Shot Font Generation},
  author = {Masaki Akiba and Shumpei Takezaki and Daichi Haraguchi and Seiichi Uchida},
  journal= {arXiv preprint arXiv:2509.10006},
  year   = {2025}
}

Comments

ICDAR 2025 Workshop on Machine Learning

R2 v1 2026-07-01T05:33:03.553Z