Visual Indeterminacy in GAN Art
Bibliographic Data
| ID | 3211697 |
|---|---|
| Authors | Aaron Hertzmann (0000-0001-9667-0292, Adobe Research 601 Townsend St San Francisco, CA 94103 U.S.A., corresponding author) |
| Year | 2020 |
| Volume | 53 |
| Issue | 4 |
| Pages | 424-428 |
| Publication date | 2020-07-01 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Leonardo (JOURNAL) |
| Journal identifiers | ISSN: 0024-094X • E-ISSN: 1530-9282 |
| Publisher | MIT Press - Journals (PUBLISHER) |
| DOI | 10.1162/leon_a_01930 |
| OpenAlex | W4231584362 |
| Language | EN |
| Citations received | 6 |
| References cited | 2 |
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
Computer vision · Epistemology · Feature (linguistics) · Generative grammar · Imperfect · Indeterminacy (philosophy) · Interpretation (philosophy) · Linguistics · Aesthetic Perception and Analysis · Artificial Intelligence · Computer Science · Generative Adversarial Networks and Image Synthesis · Image and Signal Denoising Methods · Philosophy
| Unique citing works | 6 |
|---|---|
| Citations per year | 2 |
| Citation span | 2023 - 2024 (2) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 5 |