GANs can generate photo-realistic images from the domain of their training data. However, those wanting to use them for creative purposes often want to generate imagery from a truly novel domain, a task which GANs are inherently unable to do. It is also desirable to have a level of control so that there is a degree of artistic direction rather than purely curation of random results. Here we present a method for interpolating between generative models of the StyleGAN architecture in a resolution dependent manner. This allows us to generate images from an entirely novel domain and do this with a degree of control over the nature of the output.
@article{arxiv.2010.05334,
title = {Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains},
author = {Justin N. M. Pinkney and Doron Adler},
journal= {arXiv preprint arXiv:2010.05334},
year = {2020}
}
Comments
2 pages, 3 figures. Accepted to Machine Learning for Creativity and Design NeurIPS 2020 Workshop; Corrected typos