Geometric Context from a Single Image

Geometric Context from a Single Image (2005)

by Derek Hoiem , Alexei A. Efros , Martial Hebert

Venue:	In ICCV
Citations:	111 - 27 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Geometric Context from a Single Image	user correction - Legacy Corrections
AUTHOR NAME	Derek Hoiem	SVM HeaderParse 0.2
AUTHOR AFFIL	Carnegie Mellon University	SVM HeaderParse 0.2
AUTHOR NAME	Alexei A. Efros	SVM HeaderParse 0.2
AUTHOR AFFIL	Carnegie Mellon University	SVM HeaderParse 0.2
AUTHOR NAME	Martial Hebert	SVM HeaderParse 0.2
AUTHOR AFFIL	Carnegie Mellon University	SVM HeaderParse 0.2
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 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.	user correction - Legacy Corrections
YEAR	2005	INFERENCE
VENUE	In ICCV	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	654--661	INFERENCE
VOLUME	2005	INFERENCE
CITATIONS	33 found	ParsCit 1.0