Abstract
Generative art encompasses the creation of artworks through algorithms and computational processes, allowing for the exploration of novel visual aesthetics. However, one significant drawback in this field is the reliance on simplistic techniques that limit the agent’s ability to produce complex, high-quality art. This study addresses this limitation by introducing an innovative computerized art architecture that trains a media painting model using deep reinforcement learning techniques. The model's goal is to generate a desired result using fundamental drawing behaviors, which may be generalized to diverse painting genres. In this paper, a fine-tuned trust region policy optimization approach based digital paint (art) model is developed. The suggested approach involves teaching a painting agent to produce pictures by selecting a sequence of continuous-valued activities rather than employing simplistic painting techniques. Over the boundaries of the activity areaand the agent's acquired policy, these strokes are collected on a computerized artwork that is governed by designated reference picture. Employing a learning technique, patches that are ever more complex are fed to the agent throughout training, taken from a collection of reference pictures. For successful training of the agent, loss functions like pixel-based and visual loss are generated. According to the study's findings, painting agents can pick up effective painting techniques. In results, the overall performance of our proposed framework is (converge in 98,000 episodes) achieved better outcomes. Furthermore, the agent can create complicated pictures in the specified style at random using a coarse-to-fine improvement method. This technique represents a promising direction for generative art, offering flexibility in developing excellent digital artworks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Not applicable.
Code availability
Not applicable.
References
Amadori ML, Poldi G, Camaiti M, Frezzato F, Casoli A, Germinario G, Monni E, Pedulli C, Mengacci V (2023) Giovanni Santi’s Late 15th-century paintings: microscopic, spectroscopic and chromatographic investigations on pigments, powdered glass and binding media. Appl Sci 13(17):9739
Andreotti A, Izzo FC, Bonaduce I (2023) Archaeometric study of the mural paintings by saturninogatti and workshop in the church of san Panfilo, Tornimparte (AQ): the study of organic materials in original and restored areas. Appl Sci 13(12):7153
Bergamonti L, Cirlini M, Graiff C, Lottici PP, Palla G, Casoli A (2022) Characterization of waxes in the Roman wall paintings of the Herculaneum Site (Italy). Appl Sci 12(21):11264
Borg B, Dunn M, Ang AS, Villis C (2022) Canvas painting analysis using spectroscopic analysis and microcharacterisation techniques. Sensors 22(4):1442
Casoli A (2021) Research on the organic binders in archaeological wall paintings. Appl Sci 11(19):9179
Chaban A, Tserevelakis GJ, Klironomou E, Zacharakis G, Striova J (2022) Agar gel as a non-invasive coupling medium for reflectance photoacoustic (PA) imaging: experimental results on wall-painting mock-ups. J Imag 8(9):235
Cheng M (2022) The creativity of artificial intelligence in art. In: Proceedings. 81(1): 110
Dal Fovo A, Mattana S, Chaban A, Quintero Balbas D, Lagarto JL, Striova J, Cicchi R, Fontana R (2021) Fluorescence lifetime phasor analysis and Raman spectroscopy of pigmented organic binders and coatings used in artworks. Appl Sci 12(1):179
Fulcher K, Spencer N, Budka J, Stacey RJ (2022) Polysaccharide paint binding media at two pharaonic settlements in Nubia. Heritage 5(3):2028–2040
Ibrahim B, Helwani Z, Fadhillah I, Wiranata A, Miharyono J (2021) Properties of emulsion paint with modified natural rubber latex/polyvinyl acetate blend binder. Appl Sci 12(1):296
La Nasa J, Moretti P, Maniccia E, Pizzimenti S, Colombini MP, Miliani C, Modugno F, Carnazza P, De Luca D (2020) Discovering giuseppecapogrossi: study of the painting materials in three works of art stored at galleria nazionale (rome). Heritage 3(3):965–984
Liu X, Gherbi A, Wei Z, Li W, Cheriet M (2020) Multispectral image reconstruction from color images using enhanced variational autoencoder and generative adversarial network. Ieee Access 9:1666–1679
Longoni M, Cacciola ES, Bruni S (2022) UV-excited fluorescence as a basis for the in-situ identification of natural binders in historical painting: a critical study on model samples. Chemosensors 10(7):256
Mironova A, Robache F, Deltombe R, Guibert R, Nys L, Bigerelle M (2020) Digital cultural heritage preservation in art painting: a surface roughness approach to the brush strokes. Sensors 20(21):6269
Mohie MA, Moussa A (2022) Condition assessment of a mural oil painting at fatma ismail palace, agricultural museum, Egypt. Egypt J Chem 65(132):799–810
Poli T, Chiantore O, Diana E, Piccirillo A (2021) Drying oil and natural varnishes in paintings: a competition in the metal soap formation. Coatings 11(2):171
Sun L, Chen P, Xiang W, Chen P, Gao WY, Zhang KJ (2019) SmartPaint: a co-creative drawing system based on generative adversarial networks. Front Inf Technol Electron Eng 20(12):1644–1656
Teri G, Fu P, Han K, Li J, Li Y, Jia Z, Wang Y, Li Y (2022) Color paintings of Taiping Heavenly Kingdom royal residence: AN analytical study. Coatings 12(12):1880
Turner E (2022) ‘A very curious series of paintings’: marco ricci’s paintings on leather. Restaurator Int J Preserv Lib Arch Mater 43(4):219–245
Văcar CL, Mircea C, Pârvu M, Podar D (2022) Diversity and metabolic activity of Fungi causing biodeterioration of canvas paintings. J Fungi 8(6):589
Valente J, António J, Mora C, Jardim S (2023) Developments in image processing using deep learning and reinforcement learning. J Imag 9(10):207
Varghese NV, Mahmoud QH (2021) A hybrid multi-task learning approach for optimizing deep reinforcement learning agents. IEEE Access 9:44681–44703
Wu Y, Wang P, Wang S, Liu J, Gao M, Wei R, Gao X (2020) Hyperspectral imaging and analysis for sketch painting. Optik 212:164686
Zhgun A, Avdanina D, Shumikhin K, Simonenko N, Lyubavskaya E, Volkov I, Ivanov V (2020) Detection of potential biodeterioration risks for tempera painting in 16th century exhibits from State Tretyakov Gallery. PLoS ONE 15(4):e0230591
Zou W, Yeo SY (2022) Investigation on the painting materials and profile structures used in ancient Chinese folk architectural paintings by multiple analytical methods. Coatings 12(3):320
Acknowledgements
There is no funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Ethical approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, H. A new approach to generative art using deep reinforcement learning algorithms. Int J Syst Assur Eng Manag (2024). https://doi.org/10.1007/s13198-024-02590-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13198-024-02590-7