Interpolating GANs to Scaffold Autotelic Creativity
This work addresses the challenge of creative exploration in AI-generated content for casual users, though it is incremental as it applies existing GAN interpolation to a new interactive domain.
The paper tackles the problem of generating novel hybrid animal images by interpolating categories in BigGAN's latent space, resulting in a system called 'Meet the Ganimals' that enables users to create and share these images while adapting based on user input.
The latent space modeled by generative adversarial networks (GANs) represents a large possibility space. By interpolating categories generated by GANs, it is possible to create novel hybrid images. We present "Meet the Ganimals," a casual creator built on interpolations of BigGAN that can generate novel, hybrid animals called ganimals by efficiently searching this possibility space. Like traditional casual creators, the system supports a simple creative flow that encourages rapid exploration of the possibility space. Users can discover new ganimals, create their own, and share their reactions to aesthetic, emotional, and morphological characteristics of the ganimals. As users provide input to the system, the system adapts and changes the distribution of categories upon which ganimals are generated. As one of the first GAN-based casual creators, Meet the Ganimals is an example how casual creators can leverage human curation and citizen science to discover novel artifacts within a large possibility space.