Coevolving Artistic Images Using OMNIREP

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sipper, Moshe, Moore, Jason H., Urbanowicz, Ryan J.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909078298558464
author Sipper, Moshe
Moore, Jason H.
Urbanowicz, Ryan J.
author_facet Sipper, Moshe
Moore, Jason H.
Urbanowicz, Ryan J.
contents We have recently developed OMNIREP, a coevolutionary algorithm to discover both a representation and an interpreter that solve a particular problem of interest. Herein, we demonstrate that the OMNIREP framework can be successfully applied within the field of evolutionary art. Specifically, we coevolve representations that encode image position, alongside interpreters that transform these positions into one of three pre-defined shapes (chunks, polygons, or circles) of varying size, shape, and color. We showcase a sampling of the unique image variations produced by this approach.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11167
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Coevolving Artistic Images Using OMNIREP
Sipper, Moshe
Moore, Jason H.
Urbanowicz, Ryan J.
Neural and Evolutionary Computing
We have recently developed OMNIREP, a coevolutionary algorithm to discover both a representation and an interpreter that solve a particular problem of interest. Herein, we demonstrate that the OMNIREP framework can be successfully applied within the field of evolutionary art. Specifically, we coevolve representations that encode image position, alongside interpreters that transform these positions into one of three pre-defined shapes (chunks, polygons, or circles) of varying size, shape, and color. We showcase a sampling of the unique image variations produced by this approach.
title Coevolving Artistic Images Using OMNIREP
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2401.11167