Visual Indeterminacy in GAN Art
This addresses the problem of understanding artistic qualities in AI-generated images for researchers and artists, but it is incremental as it builds on existing GAN art analysis.
The paper investigates visual indeterminacy in GAN-generated art, describing it as images that appear realistic but lack coherent spatial interpretation, and hypothesizes that this arises from the model's imperfect synthesis of objects, scenes, and textures.
This paper explores visual indeterminacy as a description for artwork created with Generative Adversarial Networks (GANs). Visual indeterminacy describes images which appear to depict real scenes, but, on closer examination, defy coherent spatial interpretation. GAN models seem to be predisposed to producing indeterminate images, and indeterminacy is a key feature of much modern representational art, as well as most GAN art. It is hypothesized that indeterminacy is a consequence of a powerful-but-imperfect image synthesis model that must combine general classes of objects, scenes, and textures.