Using reflections to see the world from new points of view

MIT researchers developed a computer vision technique that uses reflections to turn any object in a scene into a camera, allowing an observer to view the scene from that object’s point of view. The machine-learning method lets the user place a virtual camera anywhere into a scene, enabling one to see around corners or obstructions that would otherwise block the observer’s view.

Related Keywords

Nikhil Behari ,Achuta Kadambi ,Akshat Dave ,Ramesh Raskar ,Ashok Veeraraghavan ,Kushagra Tiwary ,Tzofi Klinghoffer ,National Science Foundation ,Rice University ,Camera Culture Group ,Media Lab ,Intelligence Advanced Research Projects Activity ,University Of California At Los Angeles ,Computer Vision ,Radiance Field Cameras ,Los Angeles ,National Science ,Neural Networks ,D Radiance Field ,Virtual Sensors ,