Name
Abstract | ||
|---|---|---|
Traditional image interpolation methods assume that the local spatial structure of the low-resolution (LR) and high-resolution (HR) images are approximately the same, and use edge information of the LR image to estimate the missing pixels. This assumption, however, no longer holds for natural images with fine and dense textures. Consequently, those methods cannot restore dense textures well and tend to generate over-fitting visual effects. In this paper, a learned HR image prior is exploited to overcome the problems. In particular, we use Fields of Experts (FoE) with student's t-distribution experts to model the prior, taking advantage of its representative ability of non-Gaussian natures in images. Then Maximum a Posterior (MAP) estimation incorporating FoE prior is used to estimate the missing pixels. Experimental results compared with traditional interpolation methods demonstrate that our method not only can recover fine details and produce superior PSNR values, but also avoid the visual over-fitting problems. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICIP.2009.5414396 | ICIP |
Keywords | Field | DocType |
fields of experts,fine detail,fine texturess,visual over-fitting problem,visual effect,interpolation,maximum likelihood estimation,lr image,traditional interpolation method,texture interpolation,spatial structure,traditional image interpolation method,t-distribution experts,dense texture,image interpolation methods,missing pixel,hr image,use edge information,edge information,maximum a posterior estimation,maximum a posterior (map),fine texture,image prior,nongaussian nature,fields of experts (foe),image texture,image interpolation,natural image,interpolation methods,high resolution,low resolution,markov processes,pixel,visualization,estimation | Computer vision,Markov process,Pattern recognition,Image texture,Visualization,Computer science,Interpolation,Maximum likelihood,Pixel,Artificial intelligence,Spatial structure,Image scaling | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 0 |
PageRank | References | Authors |
0.34 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kai Guo | 1 | 15 | 1.94 |
| Xiaokang Yang | 2 | 3581 | 238.09 |
| Rui Zhang | 3 | 92 | 7.65 |
| Yu Song | 4 | 356 | 52.74 |
| Hongyuan Zha | 5 | 6703 | 422.09 |