Recent advances in deep learning techniques and applications have revolutionized artistic creation and manipulation in many domains (text, images, music); however, fonts have not yet been integrated with deep learning architectures in a manner that supports their multi-scale nature. In this work we aim to bridge this gap, proposing a network architecture capable of rasterizing glyphs in multiple sizes, potentially paving the way for easy and accessible creation and manipulation of fonts.
@article{arxiv.2211.14802,
title = {Neural Font Rendering},
author = {Daniel Anderson and Ariel Shamir and Ohad Fried},
journal= {arXiv preprint arXiv:2211.14802},
year = {2022}
}