TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise

Tutkimustuotosvertaisarvioitu

Standard

Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise. / Eslahi, Nasser; Foi, Alessandro.

2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings. IEEE, 2018. 8448455.

Tutkimustuotosvertaisarvioitu

Harvard

Eslahi, N & Foi, A 2018, Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise. julkaisussa 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings., 8448455, IEEE, Zagori, Kreikka, 10/06/18. https://doi.org/10.1109/IVMSPW.2018.8448455

APA

Eslahi, N., & Foi, A. (2018). Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise. teoksessa 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings [8448455] IEEE. https://doi.org/10.1109/IVMSPW.2018.8448455

Vancouver

Eslahi N, Foi A. Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise. julkaisussa 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings. IEEE. 2018. 8448455 https://doi.org/10.1109/IVMSPW.2018.8448455

Author

Eslahi, Nasser ; Foi, Alessandro. / Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise. 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings. IEEE, 2018.

Bibtex - Lataa

@inproceedings{7d34ee3e7a634e6fb6adaf070735c6cf,
title = "Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise",
abstract = "Many approaches to compressive video recovery proceed iteratively, treating the difference between the previous estimate and the ideal video as residual noise to be filtered. We go beyond the common white-noise modeling by adaptively modeling the residual as stationary spatiotemporally correlated noise. This adaptive noise model is updated at each iteration and is highly anisotropic in space and time; we leverage it with respect to the transform spectra of a motion-compensated video denoiser. Experimental results demonstrate that our proposed adaptive correlated noise model outperforms state-of-the-art methods both quantitatively and qualitatively.",
author = "Nasser Eslahi and Alessandro Foi",
year = "2018",
month = "8",
day = "27",
doi = "10.1109/IVMSPW.2018.8448455",
language = "English",
isbn = "9781538609514",
booktitle = "2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings",
publisher = "IEEE",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Anisotropic Spatiotemporal Regularization in Compressive Video Recovery by Adaptively Modeling the Residual Errors as Correlated Noise

AU - Eslahi, Nasser

AU - Foi, Alessandro

PY - 2018/8/27

Y1 - 2018/8/27

N2 - Many approaches to compressive video recovery proceed iteratively, treating the difference between the previous estimate and the ideal video as residual noise to be filtered. We go beyond the common white-noise modeling by adaptively modeling the residual as stationary spatiotemporally correlated noise. This adaptive noise model is updated at each iteration and is highly anisotropic in space and time; we leverage it with respect to the transform spectra of a motion-compensated video denoiser. Experimental results demonstrate that our proposed adaptive correlated noise model outperforms state-of-the-art methods both quantitatively and qualitatively.

AB - Many approaches to compressive video recovery proceed iteratively, treating the difference between the previous estimate and the ideal video as residual noise to be filtered. We go beyond the common white-noise modeling by adaptively modeling the residual as stationary spatiotemporally correlated noise. This adaptive noise model is updated at each iteration and is highly anisotropic in space and time; we leverage it with respect to the transform spectra of a motion-compensated video denoiser. Experimental results demonstrate that our proposed adaptive correlated noise model outperforms state-of-the-art methods both quantitatively and qualitatively.

U2 - 10.1109/IVMSPW.2018.8448455

DO - 10.1109/IVMSPW.2018.8448455

M3 - Conference contribution

SN - 9781538609514

BT - 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2018 - Proceedings

PB - IEEE

ER -