MIT Invents AI That Can Create 3D Holograms In Real-Time
Image via Shutterstock
While virtual reality has been the way to realistically bring objects into the real world, prolonged use of VR headsets can result in nausea and eyestrain. The use of holograms, a concept that has been the fantasy of tech lovers for decades, would alleviate these problems, but they typically require an elaborate process and specialized equipment to generate.
The good news is that researchers from the Massachusetts Institute of Technology (MIT), along with Sony, have found a way to create 3D holograms in real-time—using a regular computer. The trick to it is to teach a neural network physics so that it can understand visual and depth information.
In a paper published in the Nature scientific journal, the team explained that the new deep-learning method, called tensor holography, is able to “run on a simple computer in the blink of an eye.” They developed an AI using trainable tensors that were taught to process visual and depth information in a similar way to humans.
As Entrepreneur reports, this sort of technology requires a large and comprehensive dataset, with every pixel’s color and depth data accounted for. This is necessary, as all points of an image vary in depth, and applying one operation across the board would not work.
The researchers found that tensor holography was able to generate 3D holograms from typical computer-generated images with depth data, calculated from a multi-camera configuration, in mere milliseconds.
This technology could be a game-changer for virtual reality, medical imaging, and even 3D printing, as printing with 3D holography would be quicker and more precise than layer-by-layer printing.
See how the AI works in the video below.
[via Big Think and Entrepreneur, cover image via Shutterstock]
Also check out these recent news
