Computer Vision News - April 2022

26 AI Spotlight News NVIDIA Research Turns 2D Photos Into 3D Scenes in the Blink of an AI We have already told you about NeRF (“neural radiance fields”) , an award-winning pioneering technique launched a couple of years ago at ECCV to map the color and light of 2D photos: you read about it first here and here . The challenge is to turn a collection of still images into a digital 3D scene in a matter of seconds. The NVIDIA Research team has developed an approach that almost instantly reconstructs a 3D scene from a handful of 2D images taken at different angles. The result is impressive NVIDIA Instant NeRF , that increases speed, ease and reach of 3D capture and sharing. Watch the Video Google - Recording and Translating Heart Sounds with Smartphones In different news, Greg Corrado - Head of Health AI at Google - has published a new blog relating their latest health AI developments . Close to 100,000 patients have been screened for diabetic retinopathy in project ARDA: in addition to eye disease, these fundus images can reveal cardiovascular risk factors, such as high blood sugar and cholesterol levels, with assistance from deep learning and using existing tabletop cameras in clinics. Moreover, smartphone’s built-in microphones can record heart sounds when placed over the chest to help clinicians detect heart valve disorders, such as aortic stenosis. Read More PeopleLens: Using AI to Support Social Interaction Between Children Who Are Blind and Their Peers Microsoft researchers have started PeopleLens , a new research technology that helps young people who are blind and their peers interact more easily. It’s an open-ended AI system that uses a head-mounted augmented reality device in combination with four state-of-the-art computer vision algorithms to continuously locate, identify, track, and capture the gaze directions of people in the immediate social surroundings. It creates a map of people around the user and reads out the names of people that the child looks at in spatialized audio to give him a sense of the respective positions and distances of the people around. Watch the Video Computer Vision News has found great new stories, written somewhere else by somebody else. We share them with you, adding a short comment. Enjoy!