A compendious study of super-resolution techniques by single image

Single-image Super-resolution (SISR) is the process of reconstructing a high-resolution (HR) image by artificially creating the information and frequency details from a single available low resolution (LR) image. Availability of limited number of images in the practical circumstances has motivated r...

Full description

Saved in:
Bibliographic Details
Published in:Optik (Stuttgart) 2018-08, Vol.166, p.147-160
Main Authors: Pandey, Garima, Ghanekar, Umesh
Format: Article
Language:English
Subjects:
Degradation model
Interpolation
Learning based
Regularization
Single image super-resolution
Sparse representation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Single-image Super-resolution (SISR) is the process of reconstructing a high-resolution (HR) image by artificially creating the information and frequency details from a single available low resolution (LR) image. Availability of limited number of images in the practical circumstances has motivated researchers toward this area. Plethora of techniques has been proposed over the years for SR reconstruction. In this paper, the SR process has been classified and the degradation model has been discussed. It also comprises the extensive survey of SISR techniques, including the latest developments in this field. Lastly, it covers the limitations and problems of existing techniques of SISR.
ISSN:0030-4026
1618-1336
DOI:10.1016/j.ijleo.2018.03.103