Simultaneous estimation of super-resolved intensity and depth maps from low resolution defocused observations of a scene
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Simultaneous estimation of super-resolved intensity and depth maps from low resolution defocused observations of a scene
|
|
Creator |
RAJAN, D
CHAUDHURI, S |
|
Subject |
image
restoration superresolution |
|
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. 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 focused, super-resolved image. Both the depth and the intensity maps are modeled as separate Markov random fields (MRF) and a maximum a poseteriori estimation method is used to recover the high resolution fields. Since there is no relative motion between the scene and the camera, 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 |
2011-10-26T23:41:27Z
2011-12-15T09:12:37Z 2011-10-26T23:41:27Z 2011-12-15T09:12:37Z 2001 |
|
Type |
Proceedings Paper
|
|
Identifier |
EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS,113-118
0-7695-1144-9 http://dspace.library.iitb.ac.in/xmlui/handle/10054/16168 http://hdl.handle.net/100/2776 |
|
Source |
8th IEEE International Conference on Computer Vision (ICCV 2001),VANCOUVER, CANADA,JUL 07-14, 2001
|
|
Language |
English
|
|