Abstract | ||
---|---|---|
Single image super-resolution (SR) aims at generating a high-resolution (HR) image from one low-resolution (LR) input. In this paper, we focus on single image SR by using a confidence growing model based on an example-based super resolution approach. Compared to previous works that reconstruct high-resolution image in a raster scan order, the new proposed method reconstructs the patches using a new confidence measure. More confident reconstructions are propagated to neighboring areas by enforcing a smoothness constraint in selecting patches. We also adopt hierarchical clustering to construct a training set to speed up processing. Experimental results demonstrate that this simple method outperforms existing state-of-the-art algorithms on a the given benchmark SR test images. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICIP.2014.7025798 | ICIP |
Keywords | Field | DocType |
example-based sr,confidence growing,image resolution,single image super-resolution,super-resolution,confidence growing model,hierarchical clustering,super resolution | Training set,Hierarchical clustering,Computer vision,Pattern recognition,Computer science,Raster scan,Artificial intelligence,Smoothness,Image resolution,Superresolution,Speedup | Conference |
ISSN | Citations | PageRank |
1522-4880 | 0 | 0.34 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sina Lin | 1 | 8 | 2.16 |
Zengchang Qin | 2 | 439 | 45.46 |
Renjie Liao | 3 | 204 | 13.34 |
Tao Wan | 4 | 181 | 21.18 |