1Purdue University, 2University of Chicago
Abstract
Ambigrams are calligraphic designs that have different meanings depending on the viewing orientation. Creating ambigrams is a challenging task even for skilled artists, as it requires maintaining the meaning under two different viewpoints at the same time. In this work, we propose to generate ambigrams by distilling a large-scale vision and language diffusion model, namely DeepFloyd IF, to optimize the letters' outline for legibility in the two viewing orientations. Empirically, we demonstrate that our approach outperforms existing ambigram generation methods. On the 500 most common words in English, our method achieves more than an 11.6% increase in word accuracy and at least a 41.9% reduction in edit distance.
TL;DR: We formuate ambigram generation as an optimization problem by distilling pre-trained diffusion model.
. Please refer to the paper for quantitative results.
@article{zhao2023ambigen,
title={AmbiGen: Generating Ambigrams from Pre-trained Diffusion Model},
author={Boheng Zhao and Rana Hanocka and Raymond A. Yeh},
journal={arXiv preprint arXiv:2312.02967},
year={2023}
}