Skip to content

Video Super-resolution Using Generalized Gaussian Markov Random Fields

Research output: Contribution to journalArticle (Academic Journal)

Standard

Video Super-resolution Using Generalized Gaussian Markov Random Fields. / Chen, J; Nunez-Yanez, JL; Achim, AM.

In: IEEE Signal Processing Letters, Vol. 19, 02.2012, p. 63 - 66.

Research output: Contribution to journalArticle (Academic Journal)

Harvard

APA

Vancouver

Author

Chen, J ; Nunez-Yanez, JL ; Achim, AM. / Video Super-resolution Using Generalized Gaussian Markov Random Fields. In: IEEE Signal Processing Letters. 2012 ; Vol. 19. pp. 63 - 66.

Bibtex

@article{e943d79f79de40ff9399c773428b4228,
title = "Video Super-resolution Using Generalized Gaussian Markov Random Fields",
abstract = "In this paper, we present the first application of the Generalized Gaussian Markov Random Field (GGMRF) to the problem of video super-resolution. The GGMRF prior is employed to perform a maximum a posteriori (MAP) estimation of the desired high-resolution image. Compared with traditional prior models, the GGMRF can describe the distribution of the high-resolution image much better and can also preserve better the discontinuities (edges) of the original image. Previous work had used GGMRF for image restoration in which the temporal dependencies among video frames are not considered. Since the corresponding energy function is convex, gradient descent optimisation techniques are used to solve the MAP estimation. Results show the super-resolved images using the GGMRF prior not only offers a good visual quality enhancement, but also contain a significantly smaller amount of noise.",
author = "J Chen and JL Nunez-Yanez and AM Achim",
year = "2012",
month = feb,
doi = "10.1109/LSP.2011.2178595",
language = "English",
volume = "19",
pages = "63 -- 66",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

RIS - suitable for import to EndNote

TY - JOUR

T1 - Video Super-resolution Using Generalized Gaussian Markov Random Fields

AU - Chen, J

AU - Nunez-Yanez, JL

AU - Achim, AM

PY - 2012/2

Y1 - 2012/2

N2 - In this paper, we present the first application of the Generalized Gaussian Markov Random Field (GGMRF) to the problem of video super-resolution. The GGMRF prior is employed to perform a maximum a posteriori (MAP) estimation of the desired high-resolution image. Compared with traditional prior models, the GGMRF can describe the distribution of the high-resolution image much better and can also preserve better the discontinuities (edges) of the original image. Previous work had used GGMRF for image restoration in which the temporal dependencies among video frames are not considered. Since the corresponding energy function is convex, gradient descent optimisation techniques are used to solve the MAP estimation. Results show the super-resolved images using the GGMRF prior not only offers a good visual quality enhancement, but also contain a significantly smaller amount of noise.

AB - In this paper, we present the first application of the Generalized Gaussian Markov Random Field (GGMRF) to the problem of video super-resolution. The GGMRF prior is employed to perform a maximum a posteriori (MAP) estimation of the desired high-resolution image. Compared with traditional prior models, the GGMRF can describe the distribution of the high-resolution image much better and can also preserve better the discontinuities (edges) of the original image. Previous work had used GGMRF for image restoration in which the temporal dependencies among video frames are not considered. Since the corresponding energy function is convex, gradient descent optimisation techniques are used to solve the MAP estimation. Results show the super-resolved images using the GGMRF prior not only offers a good visual quality enhancement, but also contain a significantly smaller amount of noise.

U2 - 10.1109/LSP.2011.2178595

DO - 10.1109/LSP.2011.2178595

M3 - Article (Academic Journal)

VL - 19

SP - 63

EP - 66

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

ER -