of Rembrandt’s works were analyzed over the course of 18 months, by a group of engineers, Rembrandt experts and data scientists. They then trained a deep learning engine to “paint” in the master’s signature style.
layers of pigments were printed using a 3D printer and a height map. This was made possible because the team actually used 3D scans of the heights of Rembrandt’s paintings to mimic his brushstrokes!
The number of pixels in the final result, which looks so much like a painting by Rembrandt during his lifetime that you’d be forgiven if you walked right by it in a collection of his work.