The Iconicity of the Generated Image

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: van Noord, Nanne, Garcia, Noa
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912595576881152
author van Noord, Nanne
Garcia, Noa
author_facet van Noord, Nanne
Garcia, Noa
contents How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to generate new images based on this. Given the importance of iconic images in human visual communication, as they are widely seen, reproduced, and used as inspiration, we may expect that they may similarly have a proportionally large influence within the generative AI process. In this work we explore this question through a three-part analysis, involving data attribution, semantic similarity analysis, and a user-study. Our findings indicate that iconic images do not have an obvious influence on the generative process, and that for many icons it is challenging to reproduce an image which resembles it closely. This highlights an important difference in how humans and visual generative AI models draw on and learn from prior visual communication.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Iconicity of the Generated Image
van Noord, Nanne
Garcia, Noa
Computers and Society
Computer Vision and Pattern Recognition
How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to generate new images based on this. Given the importance of iconic images in human visual communication, as they are widely seen, reproduced, and used as inspiration, we may expect that they may similarly have a proportionally large influence within the generative AI process. In this work we explore this question through a three-part analysis, involving data attribution, semantic similarity analysis, and a user-study. Our findings indicate that iconic images do not have an obvious influence on the generative process, and that for many icons it is challenging to reproduce an image which resembles it closely. This highlights an important difference in how humans and visual generative AI models draw on and learn from prior visual communication.
title The Iconicity of the Generated Image
topic Computers and Society
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.16473