ING, the Netherlands has unveiled an ambitious project that claims to bring Dutch master Rembrandt “back to life” via a 3D-printed painting. A new portrait of a man in black 17th-century clothing with a white collar and a hat was created using data from Rembrandt’s total body of work, using “deep learning” algorithms and facial recognition techniques. The portrait consists of over 148 million pixels, based on 168,263 painting fragments from Rembrandt’s art.
ING commissioned agency JWT Amsterdam to create the project to showcase what data and technology are capable of creating. Microsoft supported the project with its software and advisors from Delft University of Technology. The Mauritshuis and Museum Het Rembrandthuis also worked on the portrait.
The process involved analyzing all 346 of Rembrandt’s paintings using high resolution 3D scans and digital files, and working with Rembrandt experts to determine the subject. After this, the subject’s features were generated in the style of Rembrandt. A facial recognition algorithm identified and classified the most typical geometric patterns used by Rembrandt to paint human features, then generated new facial features for the painting. Next, these individual features were assembled into a fully formed face and bust according to Rembrandt’s use of proportions.
When the 2D version of the painting was ready, depth and texture were added. Finally, to bring the painting to life, an advanced 3D printer specially designed to make high-end reproductions of existing artwork was used.
