Sci-Fi is not fiction anymore with Osaka AI and its ability to turn thoughts into photos
As if science fiction suddenly took part in our reality, Osaka University researchers helmed an artificial intelligence that, get this, reads minds and turns them into photos using Stable Diffusion and DALL-E 2.
Brain scan images from functional magnetic resonance imaging (fMRI) are submitted to the AI. Subsequently, it decoded the brain waves and optimized text-to-image tools to convert them into pictures.
This results to the Osaka AI visualizing your thoughts or reading your mind. And to our surprise, results are around 80% accurate to what test subjects were thinking about!
Yu Takagi spearheaded his Osaka AI team that conducted the study. The University of Minnesota presented brain scans from four subjects who viewed 10,000 photos.
The AI team then trained Stable Diffusion and DALL-E to link images with specific brain activity. Other researchers have tried this approach, however, the images appeared blurry.
As a response, the researchers added captions to the images. For example, they named the image of a clock tower clock tower.
The text-to-image apps would associate brain activity with certain pictures. In turn, the Osaka AI program needed less time and data to learn how to match pictures and brain waves.
Takagi tested the system on the Minnesota samples. Here, they found the AI could recreate the images with 80% accuracy. Subsequently, he and his team confirmed the results by using brain scans from the same people looking at different images. Astoundingly, the second test produced similar results.
Keep in mind that they tested the AI system with only the same four people. Thereafter, Takagi would have to retrain the program to work on other people.
It would likely take several years before this technology becomes widely available. Yet, Iris Groen, a neuroscientist at the University of Amsterdam, remarked:
“The accuracy of this new method is impressive. These diffusion models have [an] unprecedented ability to generate realistic images.”
