Abstract | ||
---|---|---|
Learning-based super-resolution algorithms synthesize a high-resolution image based on learning patch pairs of low- and high-resolution images. However, since a low-resolution patch is usually mapped to multiple high-resolution patches, unwanted artifacts or blurring can appear in super-resolved images. In this paper, we propose a novel approach to generate a high quality, high-resolution image without introducing noticeable artifacts. Introducing robust statistics to a learning-based super-resolution, we efficiently reject outliers which cause artifacts. Global and local constraints are also applied to produce a more reliable high-resolution image. Experimental results demonstrate that the proposed algorithm can synthesize higher quality, higher-resolution images compared to the existing algorithms. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICIP.2010.5651057 | ICIP |
Keywords | Field | DocType |
multiple high-resolution patches,image resolution,reliability,learning-based super-resolution,robust learning,robust statistics,super resolution,estimation,pixel,hafnium,high resolution,training data,low resolution,robustness,algorithm design and analysis | Computer vision,Algorithm design,Pattern recognition,Computer science,Outlier,Robust learning,Robustness (computer science),Robust statistics,Artificial intelligence,Pixel,Image resolution,Superresolution | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-7993-1 | 978-1-4244-7993-1 | 1 |
PageRank | References | Authors |
0.34 | 4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Changhyun Kim | 1 | 470 | 151.39 |
Kyuha Choi | 2 | 44 | 5.32 |
Ho-young Lee | 3 | 1 | 0.34 |
Kyu-Young Hwang | 4 | 53 | 3.97 |
Jong Beom Ra | 5 | 476 | 66.96 |