A Machine Learning Application Based on Giorgio Morandi Still-Life Paintings to Assist Artists in the Choice of 3D Compositions

Salimbeni, Guido; Leymarie, Frederic Fol and Latham, William. 2022. A Machine Learning Application Based on Giorgio Morandi Still-Life Paintings to Assist Artists in the Choice of 3D Compositions. Leonardo, 55(1), pp. 57-61. ISSN 0024-094X [Article]

[img]
Preview
Text
A_Machine_Learning_application_based_on_Giorgio_Morandi_Still_Life_Paintings_to_Assist_Artists_in_the_Choice_of_3D_Compositions.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

Download (3MB) | Preview
[img]
Preview
Image
maxresdefault.jpg - Supplemental Material
Available under License Creative Commons Attribution Non-commercial.

Download (57kB) | Preview

Abstract or Description

The authors present a system built to generate arrangements of threedimensional models for aesthetic evaluation, with the aim being to support an artist in their creative process. The authors explore how this system can automatically generate aesthetically pleasing content for use in the media and design industry, based on standards originally developed in master artworks. They then demonstrate the effectiveness of their process in the context of paintings using a collection of images inspired by the work of the artist Giorgio Morandi (Bologna, 1890–1964). Finally, they compare the results of their system with the results of a well-known Generative Adversarial Network (GAN).

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.1162/leon_a_02073

Additional Information:

©2022 ISAST

Keywords:

Artificial Intelligence, ai, painting, morandi, Giorgio morandi, composition, reinforcement learning

Related URLs:

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
23 February 2022Published
November 2020Accepted

Item ID:

31665

Date Deposited:

29 Mar 2022 09:46

Last Modified:

30 Mar 2022 16:38

Peer Reviewed:

Yes, this version has been peer-reviewed.

URI:

https://research.gold.ac.uk/id/eprint/31665

View statistics for this item...

Edit Record Edit Record (login required)