A dark mountain overlooks red plains, surrounded by a strange blue shape: Three French artists provided AFP with an image generated by artificial intelligence from one of them’s brain activity. “The first,” according to the group.
“In my head, I thought strongly about the volcano,” says Pierre Vautrel, one of the Obvious members who participated in the experiment.
During an hour he spent in an MRI machine at the Brain Institute of the Pitié-Salpetriere Hospital in Paris, he imagined several scenes, each inspired by a short description. During this process, his brain activity was recorded and then processed by a specially trained artificial intelligence.
If Pierre Vautrel admits that the work produced was not exactly what he had in mind, “he retained the semantic elements: a burning mountain with flowing lava with a landscape on a light background.”
For about a year, he, Hugo Cassellis-Dupré and Gautier Vernier devoted all their energy to the “From Mind to Image” project, a project that sounds like science fiction: copying an artist’s imagination thanks to generative artificial intelligence.
“Technical prowess.”
To achieve this, these thirty-year-olds started using an existing “open source” model, MindEye, which links visual images with brain activity, and then trained their AI in several stages.
First, by streaming an artist’s portraits and landscapes into an MRI to monitor which areas of the brain are activated, and using this data to feed artificial intelligence.
This attempts to reconstruct the original images from brain data only, without seeing them during training.
The process is repeated several times for about ten hours to “create a database,” explains Hugo Cassellis-Dupré.
Second, they repeated the exercise based solely on memories of these images, before trying the experiment on pure imagination by reading “prompts,” which are descriptive texts written before entering the MRI.
“We have known for about ten years that it is possible to reconstruct the image seen through the activity of this visual cortex,” explains Alize Lopez-Bersem, a researcher at the Brain Institute and Inserm. But an “imagined” image, no. “It’s a challenge.”
Dozens of hours are necessary to sort the information collected in the MRI before submitting it to the artificial intelligence.
But, once this work is done, the image generation “is done more or less instantaneously, on very powerful computers,” as Hugo Cassellis-Dupré sums up.
“Two years ago, I would have never believed this could exist,” says Charles Millerio, a neuroradiologist involved in the trio’s research project.
For him, this “technical prowess” is linked to twofold advances in recent years: advances in medical imaging, which has made a leap forward “in terms of precision and precision,” and the impressive development of generative artificial intelligence.
The surrealism of artificial intelligence
The trio of artists also took inspiration from the Surrealist movement, which celebrates its centenary in 2024, to give their algorithmic creations their own flair.
“It is a movement in which we try to move as quickly as possible between mental image and plastic perception,” notes Pierre Vautrel, who sees in their experience a way to “reinterpret surrealism.”
“For us, there are real connections between art and science,” adds Hugo Cassellis-Dupré, who realizes that this type of technology “can be very scary if used in the wrong way.”
In the future, the three artists hope to expand their experiments to other formats, through audio or video reconstruction. Until then, they will present their various creations in October at the Danysz Gallery in Paris.
In 2018, she stunned the art world by selling for more than 400,000 euros at Christie’s in New York, a work presented as the first work produced by the artificial intelligence program “Edmond de Bellamy”, a fantastical portrait with blurred features printed on canvas.
Related Posts
At Cannes, the family red carpet for Kevin Costner and Sienna Miller
At Kalak Cinema, the return of viewers puts a smile on the faces of volunteers
