Record Details

Simultaneous estimation of super-resolved scene and depth map from low resolution defocused observations

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Simultaneous estimation of super-resolved scene and depth map from low resolution defocused observations
 
Creator RAJAN, D
CHAUDHURI, S
 
Subject varying blurred images
restoration
superresolution
recovery
noisy
super-resolution
depth from defocus
space-variant blur identification
restoration
markov random field
 
Description This paper presents a novel technique to simultaneously estimate the depth map and the focused image of a scene, both at a super-resolution, from its defocused observations. Super-resolution refers to the generation of high spatial resolution images from a sequence of low resolution images. Hitherto, the super-resolution technique has been restricted mostly to the intensity domain. In this paper, we extend the scope of super-resolution imaging to acquire depth estimates at high spatial resolution simultaneously. Given a sequence of low resolution, blurred, and noisy observations of a static scene, the problem is to generate a dense depth map at a resolution higher than one that can be generated from the observations as well as to estimate the true high resolution focused image. Both the depth and the image are modeled as separate Markov random fields (MRF) and a maximum a posteriori estimation method is used to recover the high resolution fields. Since there is no relative motion between the scene and the carriers, as is the case with most of the super-resolution and structure recovery techniques, we do away with the correspondence problem.
 
Publisher IEEE COMPUTER SOC
 
Date 2011-07-31T15:06:04Z
2011-12-26T12:53:03Z
2011-12-27T05:40:09Z
2011-07-31T15:06:04Z
2011-12-26T12:53:03Z
2011-12-27T05:40:09Z
2003
 
Type Article
 
Identifier IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 25(9), 1102-1117
0162-8828
http://dx.doi.org/10.1109/TPAMI.2003.1227986
http://dspace.library.iitb.ac.in/xmlui/handle/10054/8154
http://hdl.handle.net/10054/8154
 
Language en