Can AI Create Great Works Of Art?
By analyzing Rembrandt's oeuvre, machine learning has simulated a new work by the celebrated artist
Rembrandt, who died 347 years ago, has ‘created’ a new work all thanks to machine learning. By studying how the major Impressionist painter created his trademark spotlight effect in many of his portraits, the team at Microsoft were able to render a painting that Rembrandt, in flesh, could have painted himself.
The process began by building a 150 gigabyte-pile of data on Rembrandt’s ‘artistic DNA.’ Scans, including 2D and 3D, were upscaled with deep learning algorithms.
The ‘Next Rembrandt’ is a portrait of a man with white collar. After studying his portraits made between 1632 and 1642, the following attributes for the likely subject were discovered: Caucasian male with facial hair, in his thirties, with a white collar on black clothing, a hat and with the head tilted to the right.
To build the painting, it took computers a jarring 50 hours of rendering to come up with a 148m pixels photo. But instead of just normal printing, the final print was done in 3D.
Imitating the layers of paint that Rembrandt achieves with his materials, the team resulted to 3D layering. The final “painting” is composed of 13 layers of UV ink, printed on top of each other to create texture.
The project is presented by financial institution ING and supported by Microsoft’s Azure platform. Advisers for the project include Delft University of Technology, the Mauritshuis art museum and the Rembrandt House.
To move beyond novelty activations and one-time gimmicks, PSFK equips marketers with the insights, templates and analytics to develop high-reach campaigns that meet consumers in the moment, collect and build upon experiential data, and build scale through content creation.
At PSFK 2017, Peloton Co-Founder and COO Tom Cortese discussed how the company aims to utilize the power of Web 2.0 to marry the comfort of home fitness to the high-energy engagement of celebrity-run classes.