Bjørn Karmann created an AI prompt camera called Paragraphica, that can generate a photo using in situ to generate an AI representation of the location of the camera with added context such as weather, time of day, date, and points of interest.
Researchers from the University of California, San Francisco have developed a method that uses brain waves to identify chronic pain. By surveying patients during chronic pain episodes about their pain, with electrodes attached measuring their brain activity, the researchers created a dataset that could be used to train an AI model to detect the onset of chronic pain from brain wave measurements, and distinguish it from acute pain.
Researchers at MIT have developed an Objects as Radiance-Field Cameras (ORCa) technique that uses reflections on shiny objects as image sensors to generate viewpoints outside the view of the original camera.If you remember the Star Trek: The Next Generation episode Identity Crisis (s04e18) where Geordie recreates an incident on the holodeck and generates a previous unseen viewpoint, we can now do this with AI.
Researchers at Google released Zip-NeRF this week. A neural radiance field (NeRF) is a fully-connected neural network that can generate novel views of complex 3D scenes, based on a partial set of 2D images. Zip-NeRF incorporates complex anti-aliasing and faster training than previous NeFT system, with very impressive results.