Can AI Create Great Works Of Art?

Can AI Create Great Works Of Art?
Arts & Culture

By analyzing Rembrandt's oeuvre, machine learning has simulated a new work by the celebrated artist

Leo Lutero
  • 11 april 2016

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.

the new rembrandt 1.png
The team then used algorithms to compute Rembrandt’s ideal proportions in his paintings. Using the high definition images, software scanned and learned what geometric shapes and ratios Rembrandt used in the tiniest details of his work. Using 3D scans, the weight of the brushstrokes were analyzed and his use of materials deeply studied.

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 new rembrandt.jpg
A machine learning-generated piece poses the question: What value does a single piece have if a machine can virtually churn out innumerable works with the artist’s extracted ‘artistic DNA?’

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.

Next Rembrandt

+fashion / apparel
+microsoft azure

More in home


Nature-Inspired Rugs Portray The Effects Of Climate Change

Artist Fernando Mastrangelo's 'Reverence' collection for Edward Fields features landscape-inspired pieces

18 October 2017

Pop-Up Shops Celebrate The Ubiquitous Eames Plastic Chair

Visitors to the Vitra stores can create a custom version of the classic look by mixing and matching colors and upholstery choices

17 October 2017

The Latest


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.

October 18, 2017

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.

September 27, 2017
No search results found.