Scholarly record
ARTIFICIAL INTELLIGENCE APPLICATIONS IN VISUAL ART – CAPABILITIES, PERSPECTIVES AND LIMITATIONS
Abstract
Nowadays artificial intelligence (AI) enters almost all aspects of human life. AI, undergoing dynamic development thanks to a rapid progress in computer and information technology, delivers powerful algorithms that more and more replace humans and their natural intelligence in a great many tasks, like natural language processing and understanding (NLP), forecasting, speech recognition, pattern identification and classification, image understanding, work automation, and many more. But what about art? Can AI replace natural human creativity, can it design and make outstanding artworks? The paper, generally answering “yes” to above mentioned questions, shows also both perspectives and limitations of AI possibilities in this domain. It presents the selected, important aspects of AI application in visual art, concentrating on: introducing AI tools (especially Generative Adversarial Neural Networks) used in AI-supported image creation, analysis of development of AI-based art perceived as a new direction in contemporary art, and presenting examples of AI artworks. Author’s propositions and considerations concerning future AI-based art tools development, together with analysis of their limitations (with reference to some currently considered philosophical aspects concerning AI) are presented. Finally, author proposes a kind of Turing test dedicated for AI-based visual art.
Publication Impact Profile
- Captures
- Mendeley - Readers: 4
Publication details
References7
Aggarwal C.C., Neural Networks and Deep Learning: A Textbook, Springer, 2018.
Elgammal A., Liu B., Elhoseiny M., Mazzone M., CAN: Creative Adversarial Networks Generating “Art” by Learning About Styles and Deviating from Style Norms, arXiv:1706.07068v1 [cs.AI], 2017.
Gonsalves R.A., GANscapes: Using AI to Create New Impressionist Paintings, https://towardsdatascience.com/ganscapes-using-ai-to-create-new-impressionistpaintings-d6af1cf94c56, 2021.
Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y., Generative Adversarial Nets, Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014), pp. 2672–2680, 2014.
Hockney D., Secret Knowledge: Rediscovering the lost technique of the Old Masters, Thames & Hudson, London, 2006.
Morajda J., Paliwoda-Pekosz G., A Concept of FLOPM: Neural Maps with Floating Nodes for Classification and Prediction, AMCIS 2021 Proceedings, 16, 2021.
Shahriar S., GAN Computers Generate Arts? A Survey on Visual Arts, Music, and Literary Text Generation using Generative Adversarial Network, arXiv:2108.03857 [cs.AI], 2021.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.