Geometric context from a single image

Derek Hoiem, Alexei A. Efros, Martial Hebert

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages654-661
Number of pages8
DOIs
StatePublished - Dec 1 2005
Externally publishedYes
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: Oct 17 2005Oct 20 2005

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
VolumeI

Other

OtherProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
CountryChina
CityBeijing
Period10/17/0510/20/05

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Geometric context from a single image'. Together they form a unique fingerprint.

Cite this