Title | ||
---|---|---|
Improvement on learning-based super-resolution by adopting residual information and patch reliability |
Abstract | ||
---|---|---|
Learning-based super-resolution algorithms synthesize high-resolution details by using training data. However, since an input image does not belong to a training image set, there is a limitation in recovering its high-frequency details. In our approach, we build and utilize residual training data to complement missing details. We first estimate a pair of mid- and high-frequency images of each training image by using ordinary training data. We then build residual training data by obtaining the residual mid-and high-frequency images that denote the difference between the estimation and original. Thereby, we can synthesize high-resolution details better by using both ordinary and residual training data sets. In addition, in order to use training data more efficiently, we adaptively select low-resolution patches in an input image. Experimental results demonstrate that the proposed method can synthesize higher-resolution images compared to the existing algorithms. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICIP.2009.5413697 | ICIP |
Keywords | Field | DocType |
higher-resolution image,residual,high-resolution detail,learning (artificial intelligence),image resolution,patch reliability,residual training data,training image,residual training data set,super-resolution,learning based super resolution,ordinary training data,high-frequency image,input image,training image set,residual information adoption,reliability,learning-based super-resolution,residual information,learning,training data,interpolation,correlation,high resolution,super resolution,low resolution,high frequency,learning artificial intelligence | Training set,Computer vision,Residual,Pattern recognition,Computer science,Interpolation,Artificial intelligence,Training data sets,Superresolution,Image resolution | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 4 |
PageRank | References | Authors |
0.39 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Changhyun Kim | 1 | 470 | 151.39 |
Kyuha Choi | 2 | 44 | 5.32 |
Jong Beom Ra | 3 | 476 | 66.96 |