Geometric Context from a Single Image

Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes. Geometric classes describe the 3D orientation of an image region with respect to the camera. We provide a multiplehypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label. These confidences can then be used to improve the performance of many other applications. We provide a thorough quantitative evaluation of our algorithm on a set of outdoor images and demonstrate its usefulness in two applications: object detection and automatic singleview reconstruction.

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: Derek Hoiem, Alexei A. Efros, Martial Hebert
• Keywords: Cluttered Natural Scenes, Coarse Geometric Properties, Computer Vision, Geometric Classes, Geometric Label, Geometric Structure, ICCV 2005