Learning Implicit Glyph Shape Representation

TL;DR

This paper introduces a new implicit glyph shape representation using quadratic curves, enabling high-resolution image generation, effective font style transfer, and potential vector font conversion, advancing 2D shape modeling.

Contribution

The paper proposes a structured implicit glyph representation and a disentangled network for one-shot font style transfer, outperforming existing methods.

Findings

Effective for font reconstruction and interpolation

Achieves state-of-the-art results in style transfer

Potential for converting glyphs to vector fonts

Abstract

In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Experiments on font reconstruction and interpolation tasks verified that this structured implicit representation is suitable for describing both structure and style features of glyphs. Furthermore, based on the proposed representation, we design a simple yet effective disentangled network for the challenging one-shot font style transfer problem, and achieve the best results comparing to state-of-the-art alternatives in both quantitative and qualitative comparisons. Benefit from this representation, our generated glyphs have the potential to be converted to vector fonts through post-processing, reducing the gap between rasterized images and vector graphics. We hope this work can provide a powerful tool for 2D shape analysis and synthesis, and inspire further exploitation in implicit representations for 2D shape modeling.