Year: 2021
Type: preprint
Abstract: Recently, the discovery of interpretable directions in the latent spaces of pre-trained GANs has become a popular topic. While existing works mostly consider directions for semantic image manipulations, we focus on an abstract property: creativity. Can we manipulate an image to be more or less creative? We build our work on the largest AI-based creativity platform, Artbreeder, where users can generate images using pre-trained GAN models. We explore the latent dimensions of images generated on this platform and present a novel framework for manipulating images to make them more creative. Our code and dataset are available at http://github.com/catlab-team/latentcreative.
Source: arXiv (Cornell University)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4226072848