Scientists Are Training A.I. to Reconstruct Long-Lost Underpaintings by Artists Including Van Gogh and Leonardo da Vinci

The team has also started using DALL-E to reconstruct lost masterpieces known only through textual descriptions.

Reconstruction of Vincent Van Gogh, Two Wrestlers by Oxia Palus. Photo courtesy of Oxia Palus.

An underpainting of two male wrestlers discovered via X-ray beneath a still life by Vincent Van Gogh has been reconstructed into a work in its own right by artificial intelligence. 

The picture, which is being exhibited by MORF Gallery at the Focus Art Fair in the Louvre (through September 4), was carried out by Oxia Palus, an initiative run by physicist George Cann and neuroscientist Anthony Bourached, both PhD students at University College London, alongside the artist Jesper Eriksson. 

The image, which shows the two topless figures in close combat, was first discovered a decade ago. It was painted over with Still life with meadow flowers and roses (1886), now at at the Kröller-Müller Museum in the Netherlands.

A reference to the lost work exists in a letter by Van Gogh to his brother Theo from January 1886, which reads: “This week I painted a large thing with two nude torsos—two wrestlers […] and I really liked doing that.”

Though the reconstruction of its color and style is an estimation made by the A.I., Bourached said it was “very convincing—by far the best guess we can get with current technology.”

To get A.I. to reproduce the style of an Old Master, the team trained a neural network on other examples of the artist’s work, teaching it to accurately reconstruct the picture from an X-ray-style image.

Reconstruction of Titian, Psyche and Cupid by Oxia Palus. Photo courtesy of Oxia Palus.

Two Wrestlers is one of several works that have been resurrected by Oxia Palus. Known as the NeoMasters, the collection includes a standing female nude hidden behind another of Van Gogh’s paintings, a portrait of Modgliani’s ex-lover Beatrice Hastings behind the Italian artist’s Portrait of a Girl (1917), and The Lonesome Crouching Nude from behind Picasso’s The Blind Man’s Meal (1903). 

A landscape painting of the Parc del Laberint d’Horta in Barcelona by Santiago Rusiñol was also recreated after disappearing behind Picasso’s The Crouching Beggar.

This August, Oxia Palus also initiated TextMasters, a new series that uses the A.I. text-to-image generator DALL-E 2 to reconstruct lost masterpieces known to us only by text descriptions. 

So far, the collection includes Velázquez’s Cupid and Psyche, Titian’s Ixion and—having just dropped today—Leonardo da Vinci’s Medusa. The images are being sold as NFTs on KnownOrigin. 

Delving into the process behind recreating Cupid and Psyche, Eriksson told Artnet News it was just a matter of using a simple prompt: “a portrait by Velázquez of a woman called Psyche embracing Cupid in a darkened room.” 

“Whilst the prompt is rather simple we’ve found that DALL-E, like many text models, often responds well to certain key phrases rather than lengthy descriptions,” he said. “For instance, ‘a woman called Psyche’ seemed to clue the model into the female-male relationship between the two subjects.”

“‘Embracing’ set the detail of that relationship up and also their spatial composition, whilst ‘darkened room’ seemed to provide an accurate scene, which when combined with its training data from other works by Velazquez pulled out a color scheme similar to what we were looking for.”


Follow Artnet News on Facebook:


Want to stay ahead of the art world? Subscribe to our newsletter to get the breaking news, eye-opening interviews, and incisive critical takes that drive the conversation forward.

artnet and our partners use cookies to provide features on our sites and applications to improve your online experience, including for analysis of site usage, traffic measurement, and for advertising and content management. See our Privacy Policy for more information about cookies. By continuing to use our sites and applications, you agree to our use of cookies.

Subscribe or log in to read the rest of this content.

You are currently logged into this Artnet News Pro account on another device. Please log off from any other devices, and then reload this page continue. To find out if you are eligible for an Artnet News Pro group subscription, please contact [email protected]. Standard subscriptions can be purchased on the subscription page.

Log In