Axial Generation: Mixing Colour and Shapes to Automatically Form Diverse Digital Sculptures

Abstract

Automated computer generation of aesthetically pleasing artwork has been the subject of research for several decades. The unsolved problem of interest is how to please any audience without requiring too much of their involvement in the process of creation. Two-dimensional pictures have received a lot of attention; however, 3D artwork has remained relatively unexplored. This paper showcases an extended version of the Axial Generation Process (AGP), a versatile generation algorithm that can create both 2D and 3D items within the Concretism art style. The extensions presented here include calculating colour values for the artwork, increasing the range of forms that can be created through dynamic sizing of shapes and including more primitive shape types, finally, 2D items can be created from multiple viewpoints. Both 2D and 3D items generated through the AGP were evaluated against a set of formal aesthetic measures and compared against two established generation systems, one based on manipulating pixels/voxels and another tracking the path of particles through 2D and 3D space. This initial evaluation shows that the process is capable of generating visually varied items which exhibit a generally diverse range of values across the measures used, in both two and three dimensions. Comparatively, against the established generation processes, the AGP shows a good balance of performance and ability to create complex and visually varied items.

Publication DOI: https://doi.org/10.1007/s42979-022-01329-0
Divisions: College of Engineering & Physical Sciences > Aston Institute of Urban Technology and the Environment (ASTUTE)
?? 50811700Jl ??
College of Engineering & Physical Sciences
Additional Information: © The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License (CC-BY)
Uncontrolled Keywords: Original Research,Evolutionary Art and Music,Evolutionary computation,2D and 3D art generation,Concretism
Publication ISSN: 2661-8907
Last Modified: 04 Jul 2024 07:12
Date Deposited: 07 Oct 2022 08:17
Full Text Link:
Related URLs: https://link.sp ... 22-01329-0#Sec1 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2022-11
Published Online Date: 2022-10-05
Accepted Date: 2022-07-14
Submitted Date: 2021-07-28
Authors: Easton, Edward
Ekárt, Anikó (ORCID Profile 0000-0001-6967-5397)
Bernardet, Ulysses (ORCID Profile 0000-0003-4659-3035)

Download

[img]

Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Statistics

Additional statistics for this record