Record Details

Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera
 
Creator NAMBOODIRI, VP
CHAUDHURI, S
 
Subject defocused images
enhancement
filters
field
 
Description In this paper we investigate the challenging problem of recovering the depth layers in a scene from a single defocused observation. The problem is definitely solvable if there are multiple observations. In this paper we show that one can perceive the depth in the scene even from a single observation. We use the inhomogeneous reverse heat equation to obtain an estimate of the blur, thereby preserving the depth information characterized by the defocus. However, the reverse heat equation, due to its parabolic nature, is divergent. We stabilize the reverse heat equation by considering the gradient degeneration as an effective stopping criterion. The amount of (inverse) diffusion is actually a measure of relative depth. Because of ill-posedness we propose a graph-cuts based method for inferring the depth in the scene using the amount of diffusion as a data likelihood and a smoothness condition on the depth in the scene. The method is verified experimentally on a varied set of test cases.
 
Publisher IEEE
 
Date 2011-10-27T19:34:34Z
2011-12-15T09:12:47Z
2011-10-27T19:34:34Z
2011-12-15T09:12:47Z
2008
 
Type Proceedings Paper
 
Identifier 2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12,3399-3404
978-1-4244-2242-5
1063-6919
http://dspace.library.iitb.ac.in/xmlui/handle/10054/16399
http://hdl.handle.net/100/2892
 
Source IEEE Conference on Computer Vision and Pattern Recognition,Anchorage, AK,JUN 23-28, 2008
 
Language English