A Neuroscientist and a Physicist Used AI to Recreate a Lost Painting Buried Under a Beloved Picasso Canvas
To mark the 48th anniversary of Pablo Picasso’s death, today two scientists working at the intersection of art and artificial intelligence are releasing a series of NFTs based on the recreation of a lost work of art hidden under one of the famous artist’s finished canvases. probably by Santiago Rusiñol.
The project, called Oxia Palus, was initiated by two PhD students from University College London, Anthony Bourached and George Cann. It uses machine learning, deep networks, and neural-style transmission algorithms developed by researchers at the University of Tübingen in Germany to analyze ghostly X-rays of overpainted works of art. Based on the known works of the artist, the computer can create a full color version of the lost composition.
The duo first tested the process in Picasso’s The Old Guitarist and published their results in 2019 in an article entitled “Raiders of the Lost Art”.
To date, Oxia Palus has created color images of 20 lost paintings, which previously could only be seen by X-ray. The next step was to use 3D printing technology to create textured canvases of the lost paintings with realistic brush strokes.
“There are potentially thousands of works that we got to see over the next several years that haven’t been seen in hundreds of years,” Cann told Artnet News.
It’s an unlikely project for two scientists. Bourached’s studies deal with high-dimensional neuroscience, while Cann deals with efforts to discover life on Mars. The name Oxia Palus actually comes from Cann’s dissertation.
“It’s a region of Mars that has a lot of interest in finding life, especially underground,” Cann said. “In an analogous sense, by exploring this world and finding life beneath it, we are doing a very similar thing, but beneath the surface of color.”
Bourached and Cann named their high-tech replicas “NeoMasters” and hope to one day apply the same process to lost works for which there is only a written description.
“This is in contrast to a lot of current AI artwork that is about creating something new and creative,” Bourached told Artnet News. “We look back on artists who have withstood the filter of time in terms of cultural, social and historical effects.”
The first physical replica of a lost painting comes from Picasso’s work La Miséreuse Accroupie (The Crouching Beggar) from 1902. As a young artist in Barcelona who could not afford new art objects, he painted it on an existing work by one of his contemporaries.
References to this lost painting could be seen through cracks on the surface of the work, revealing traces of the other composition below. It wasn’t until the Art Gallery of Ontario, which owns the piece, examined it with a portable X-ray fluorescence scanner in 2018 that the lost composition came to light.
The original painting is believed to represent a hilly landscape in the Jardin Laberint d’Horta in Barcelona. Rusiñol, the leader of the Catalan modernism movement, is one of the most likely candidates for its authorship.
Based on this assumption, Bourached and Cann trained the AI in Rusiñol’s style and generated a possible color version of the recently discovered X-ray.
The duo then created an edition of 100 3D-printed canvases of the lost painting, each linked to an NFT in a blockchain.
“It’s something that has never been done before and is a patent pending approach for us,” said Bourached. “The layering of this paint and ink on a canvas is advancing the state of the art in 3D printing technology.”
The editions, which are available at the MORF Gallery for $ 11,111.11 each, also feature anti-fraud technology with a unique code linked to the associated NFT colored on the canvas below. (The images can only be purchased in traditional dollars, not in cryptocurrency.)
There are no plans to donate any of the copies to the AGO, but Bourached and Cann hope that Oxia Palus can work with institutions in the future.
“From an educational point of view,” said Bourached, “it would be amazing if you could have both pieces side by side in a museum.”
Follow Artnet News on Facebook:
Do you always want to be one step ahead of the art world? Subscribe to our newsletter for the latest news, insightful interviews, and succinct critical attitudes that keep the conversation moving.