Abstract | ||
---|---|---|
In many real applications traditional superresolu- tion methods fail to provide high-resolution images due to objectionable blur and inaccurate registration of in- put low-resolution images. In this paper, we present a method of superresolution and blind deconvolution of video sequences and address problems of misregis- tration, local motion and change of illumination. The method processes the video by applying temporal win- dows, masking out regions of misregistration, and mini- mizing a regularized energy function with respect to the high-resolution frame and blurs, where regularization is carried out in both the image and blur domains. Ex- periments on real video sequences illustrate robustness of the method. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4760989 | Tampa, FL |
Keywords | Field | DocType |
deconvolution,image registration,image sequences,video signal processing,blind video deconvolution,image registration,video sequences,video superresolution | Computer vision,Masking (art),Blind deconvolution,Pattern recognition,Computer science,Deconvolution,Robustness (computer science),Regularization (mathematics),Pixel,Artificial intelligence,Image resolution,Image registration | Conference |
ISSN | ISBN | Citations |
1051-4651 E-ISBN : 978-1-4244-2175-6 | 978-1-4244-2175-6 | 5 |
PageRank | References | Authors |
0.46 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Filip Sroubek | 1 | 149 | 7.80 |
J. Flusser | 2 | 398 | 25.42 |
Michal Sorel | 3 | 5 | 0.46 |