In this work, we present a method for single-view reasoning about 3D surfaces and their relationships. We propose the use of mid-level constraints for 3D scene understanding in the form of convex and concave edges and introduce a generic framework capable of incorporating these and other constraints. Our method takes a variety of cues and uses them to infer a consistent interpretation of the scene. We demonstrate improvements over the state-of-the art and produce interpretations of the scene that link large planar surfaces.
This is a joint work with Abhinav Gupta and Martial Hebert.
David Fouhey is a Ph.D. student at the Robotics Institute, Carnegie Mellon University, where he is supervised by Abhinav Gupta and Martial Hebert. He holds an A.B. in Computer Science from Middlebury College. His research addresses a variety of scene understanding tasks in computer vision, with a particular interest in inferring 3D properties of a scene from a single image.
Host: Kris Kitani