Visual Indeterminacy in GAN Art
#SIGGRAPH_2020_Art_papers
hr.icon
DOI (ACM Digital Library)：https://doi.org/10.1145/3386567.3388574
Title
Visual Indeterminacy in GAN Art
https://gyazo.com/4f22874311233a5ef9993cb7484fe2de
Artist
Aaron Hertzmann
Abstract
This paper explores visual indeterminacy as a description for artwork created with Generative Adversarial Networks (GANs). Visual indeterminacy describes images that 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. The author hypothesizes that indeterminacy is a consequence of a powerful-but-imperfect image synthesis model that must combine general classes of objects, scenes and textures.