What primitives should we use to infer the rich 3D world behind an image?
We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.
David Fouhey is a 3rd year Ph.D. student in the Robotics Institute, where he is supervised by Abhinav Gupta and Martial Hebert. He holds an A.B. in Computer Science from Middlebury College. His research focuses on computer vision and machine learning and he is particularly interested in single-view scene understanding problems.
Host: Kris Kitani