Abstract
In the past few years deep-learning AI neural networks have achieved major milestones in artistic image analysis and generation, producing what some refer to as ‘art.’ We reflect critically on some of the artistic shortcomings of a few projects that occupied the spotlight in recent years. We introduce the term ‘Zombie Art’ to describe the generation of new images of dead masters, as well as ‘The AI Reproducibility Test.’ We designate the problems inherent in AI and in its application to art history. In conclusion, we propose new directions for both AI-generated art and art history, in the light of these new powerful AI technologies of artistic image analysis and generation.
Highlights
Artificial Intelligence (AI) has been in the public eye and imagination for many years already, with endless scenarios describing the disappearance of different jobs and human skills, which would be overtaken by intelligent machines
While we applaud the progress in machine learning, neural nets, image recognition and manipulation, we question whether they constitute a major artistic breakthrough, at least in their current form
For the purpose of our discussion we rely on three AI art projects that have attracted a substantial amount of media attention recently: The Dutch Rembrandt project, created by a multidisciplinary group of researchers, analyzed the style and content of a large number of Rembrandt’s paintings with customcreated AI, used the data to produce a “new Rembrandt portrait” (ING et al, 2016); The DEEPART project, created by a German group of computer scientists, provides proof of concept that AI can successfully separate the content of an image from its style, to combine the style of one image with the content of another
Summary
Artificial Intelligence (AI) has been in the public eye and imagination for many years already, with endless scenarios describing the disappearance of different jobs and human skills, which would be overtaken by intelligent machines. For the purpose of our discussion we rely on three AI art projects that have attracted a substantial amount of media attention recently: The Dutch Rembrandt project, created by a multidisciplinary group of researchers, analyzed the style and content of a large number of Rembrandt’s paintings with customcreated AI, used the data to produce a “new Rembrandt portrait” (ING et al, 2016); The DEEPART project, created by a German group of computer scientists, provides proof of concept that AI can successfully separate the content of an image from its style, to combine the style of one image with the content of another Their well-known example is an image that reproduces a picture of the contemporary city of Tübingen in the style of Van Gogh’s Starry Night. A slightly different project was created by the Parisian collective, Obvious Art. The collective generated painterly portraiture images based on a large dataset of 14th to 20th century portraits analyzed by a deep learning neural net.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
