#EpicMonetGuy

Eurovision’s Epic Sax Guy in the style of Monet’s Poppyfield in Giverny, using state-of-the-art Deep Learning algorithms. #EpicMonetGuy is a reaction to the disposable, sensationalist, instant-gratification-seeking, click-bait ‘art & entertainment’ extravaganza and related debates in the internet age.

There has been an explosion in Artificial Intelligence Deep Learning research recently, allowing images to be synthesised in various novel ways. These include algorithms which can ‘learn’ the ‘style’ of a particular painting (e.g. Monet, Van Gogh etc) and ‘apply’ it to a photograph. While this research is still very much in its infancy, it is already technically ground-breaking, and examples of these algorithms have gone viral on social (and subsequently on mainstream) media with hashtags such as #Deepdream, #NeuralDoodle, #StyleTransfer etc, (also recently resulting in an Art of Neural Networks exhibition at the Gray Area Foundation in San Francisco). However, the general discussions on media have mostly chosen to focus on rather unimaginative and unproductive angles such as ‘computers can be creative for you so now you don’t have to be’, ‘filters to create instant art’, ‘create art by painting like Monet or Van Gogh’ etc.,- even ranging to the more sensationalist and desperate angles such as ‘Skynet is coming’. While these developments actually open so many opportunities to critically discuss human-machine interaction in the context of creativity and creative expression, the popularity of the narratives around trying to reduce ‘the creation of art’ to a one-button-click process; ignoring or off-loading all sense of vision, creativity, intentionality, responsibility or skill to a piece of software; shared via click-bait headlines or throwaway comments on social media or news sites; these discussions simultaneously expose our obsessions for sensationalism, instant gratification and disposable debate. #EpicMonetGuy is a reaction to all of this.

The mentioned research includes:

Made with Adam Wentz’s Neural Image Analogies research.

Ten hour version with audio on gifsound.