Carnegie Mellon University
Geometric Context from a Single Image

Derek Hoiem, Alexei A. Efros, and Martial Hebert
International Conference of Computer Vision (ICCV), October, 2005, pp. 654 - 661.

  • Adobe portable document format (pdf) (8MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

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 multiple-hypothesis 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 single-view reconstruction.

geometry, context, object detection

Associated Project(s): Object Recognition Using Statistical Modeling and Geometrically Coherent Image Interpretation
Number of pages: 8

Text Reference
Derek Hoiem, Alexei A. Efros, and Martial Hebert, "Geometric Context from a Single Image," International Conference of Computer Vision (ICCV), October, 2005, pp. 654 - 661.

BibTeX Reference
   author = "Derek Hoiem and Alexei A. Efros and Martial Hebert",
   title = "Geometric Context from a Single Image",
   booktitle = "International Conference of Computer Vision (ICCV)",
   pages = "654 - 661",
   publisher = "IEEE",
   month = "October",
   year = "2005",
   volume = "1",