You’ve heard of a Pink Floyd song reconstructed from brain recordings, but now, researchers successfully used AI to reconstruct images from human brain waves with 75.6% accuracy. This new method leverages the Bayesian estimation framework while introducing the assistance of semantic information into it.
The framework managed to successfully reconstruct both seen images (i.e., those observed by the human eye) and imagined images from brain activity. How was this achieved? Test subjects viewed 1,200 various images while situated in a functional magnetic resonance imaging (fMRI) machine. They were shown an image different from the 1,200 viewed, and their brain activity was measured under the fMRI 30-60 minutes later while asked to imagine what kind of image they viewed. A generative AI program reconstructed the image, undergoing a 500-step revision process.
No products found.
In contrast, the previous method could only identify seen images (seen: 64.3%, imagery: 50.4%). These results suggest that our framework would provide a unique tool for directly investigating the subjective contents of the brain such as illusions, hallucinations, and dreams,” said the researchers.
