Few-Shot Font Generation with Deep Metric Learning

TL;DR

This paper presents a deep metric learning-based framework for automatic Japanese font generation from limited samples, achieving coherent and high-quality glyph synthesis despite extremely few style references.

Contribution

It introduces a novel deep metric learning approach to improve style feature extraction for few-shot font generation, addressing limitations of existing methods.

Findings

Effective in generating coherent glyphs with few samples

Outperforms existing methods in quality and style consistency

Validated on diverse font datasets

Abstract

Designing fonts for languages with a large number of characters, such as Japanese and Chinese, is an extremely labor-intensive and time-consuming task. In this study, we addressed the problem of automatically generating Japanese typographic fonts from only a few font samples, where the synthesized glyphs are expected to have coherent characteristics, such as skeletons, contours, and serifs. Existing methods often fail to generate fine glyph images when the number of style reference glyphs is extremely limited. Herein, we proposed a simple but powerful framework for extracting better style features. This framework introduces deep metric learning to style encoders. We performed experiments using black-and-white and shape-distinctive font datasets and demonstrated the effectiveness of the proposed framework.