Title | ||
---|---|---|
Single image example-based super-resolution using cross-scale patch matching and markov random field modelling |
Abstract | ||
---|---|---|
Example-based super-resolution has become increasingly popular over the last few years for its ability to overcome the limitations of classical multi-frame approach. In this paper we present a new example-based method that uses the input low-resolution image itself as a search space for high-resolution patches by exploiting self-similarity across different resolution scales. Found examples are combined in a highresolution image by the means of Markov Random Field modelling that forces their global agreement. Additionally, we apply back-projection and steering kernel regression as post-processing techniques. In this way, we are able to produce sharp and artefact-free results that are comparable or better than standard interpolation and state-of-the-art super-resolution techniques. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-21593-3_2 | ICIAR |
Keywords | Field | DocType |
state-of-the-art super-resolution technique,markov random field modelling,input low-resolution image,example-based super-resolution,artefact-free result,cross-scale patch matching,classical multi-frame approach,different resolution scale,global agreement,highresolution image,single image,high-resolution patch | Pattern recognition,Computer science,Markov random field,Interpolation,Artificial intelligence,Superresolution,Kernel regression | Conference |
Volume | ISSN | Citations |
6753 | 0302-9743 | 2 |
PageRank | References | Authors |
0.37 | 13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tijana Ružić | 1 | 35 | 3.37 |
Hiêp Q. Luong | 2 | 27 | 2.12 |
Aleksandra Pizurica | 3 | 1238 | 102.29 |
Wilfried Philips | 4 | 115 | 10.61 |