![]() The results were instead amorphous works of abstract art that resembled an objects’ overall position and perspective but were otherwise unrecognizable.Īlthough the AI would likely perform better with more information to draw from, scientists were limited by the data at hand. ![]() There was just one problem: when the AI analyzed a brain scan, it could roughly approximate scale and perspective - information gathered from the occipital lobe - but couldn’t discern exactly what the object was. ![]() Using patterns of brain activity alone (middle), Stable Diffusion can reproduce the layout and perspective, but with captions (right), it can also more accurately recreate the original image. Left is the image as seen by study participants.
0 Comments
Leave a Reply. |