Artificial intelligence is developing rapidly. What AI is capable of today? It recognizes faces, creates new drugs and even writes music. And this, of course, is far from all. This time, the power of artificial intelligence fell on the picture of Pablo Picasso’s “Old Guitarist”. However, the first thing that was recognised by AI on the canvas was the silhouette of a seated woman. In 1998, scientists looked under the top layer of paint in the picture and found there the original drawing of Picasso. Today, thanks to artificial intelligence, you and I can enjoy this hidden work of art.
It is a fact that a lot of famous artists often painted on top of ready-made paintings. Among them are paintings by such talented artists as Leonardo da Vinci, Rembrandt and Van Gogh. To see the artist’s original image on canvas, experts used an x-ray technique, which uses x-rays and infrared light. This method previously allowed scientists to determine that Pablo Picasso has hidden other paintings under the other, “The Crouching Beggar” and “The Old Guitarist”.
By using a neural network trained to distinguish the style of one artist from another, researchers from University College London breathed new life into the picture, recreating the original Picasso.
The basis for the neural network was the technique developed in 2015 by Leon Gatis, called the transmission of the neural style. Computer vision technology can determine the style of painting and transform it into a style of another painting. During the study, scientists took X-ray images of the outlines of a woman and connected them to a neural network created to convert images into the style of the blue period of Picasso. Although the result cannot accurately recreate the painting created by Picasso more than a century ago, the resulting image corresponds to the style in which the artist painted his paintings in those years. The authors of the study believe that their work will inspire similar projects to search for lost works of art.
Artificial Intelligence recreates Pablo Picasso’s paintings
26
September
2019