TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise

Tutkimustuotosvertaisarvioitu

Standard

Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise. / Mäkinen, Ymir; Azzari, Lucio; Foi, Alessandro.

2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. s. 185-189 (IEEE International Conference on Image Processing).

Tutkimustuotosvertaisarvioitu

Harvard

Mäkinen, Y, Azzari, L & Foi, A 2019, Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise. julkaisussa 2019 IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing, IEEE, Sivut 185-189, IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 1/01/00. https://doi.org/10.1109/ICIP.2019.8802964

APA

Mäkinen, Y., Azzari, L., & Foi, A. (2019). Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise. teoksessa 2019 IEEE International Conference on Image Processing (ICIP) (Sivut 185-189). (IEEE International Conference on Image Processing). IEEE. https://doi.org/10.1109/ICIP.2019.8802964

Vancouver

Mäkinen Y, Azzari L, Foi A. Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise. julkaisussa 2019 IEEE International Conference on Image Processing (ICIP). IEEE. 2019. s. 185-189. (IEEE International Conference on Image Processing). https://doi.org/10.1109/ICIP.2019.8802964

Author

Mäkinen, Ymir ; Azzari, Lucio ; Foi, Alessandro. / Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise. 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. Sivut 185-189 (IEEE International Conference on Image Processing).

Bibtex - Lataa

@inproceedings{0c946754900d42a9889022ae9b1767b0,
title = "Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise",
abstract = "Collaborative filters perform denoising through transform-domain shrinkage of a group of similar blocks extracted from an image. Existing methods for collaborative filtering of stationary correlated noise have all used simple approximations of the transform noise power spectrum adopted from methods which do not employ block grouping. We note the inaccuracies of these approximations and introduce a method for the exact computation and effective approximations of the noise power spectrum. Unlike earlier methods, the calculated noise variances are exact even when noise in one block is correlated with noise in any of the other blocks. We discuss the adoption of the exact noise power spectrum within shrinkage, in similarity testing (block matching), and in aggregation. Extensive experiments support the proposed method over earlier crude approximations used by image denoising filters such as BM3D, demonstrating dramatic improvement in many challenging conditions.",
keywords = "Two dimensional displays, Reactive power, Transforms, Collaboration, Three-dimensional displays, Noise reduction, Noise measurement, Image denoising, correlated noise, collaborative filtering, noise power spectrum, BM3D",
author = "Ymir M{\"a}kinen and Lucio Azzari and Alessandro Foi",
year = "2019",
month = "9",
doi = "10.1109/ICIP.2019.8802964",
language = "English",
isbn = "978-1-5386-6250-2",
series = "IEEE International Conference on Image Processing",
publisher = "IEEE",
pages = "185--189",
booktitle = "2019 IEEE International Conference on Image Processing (ICIP)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Exact Transform-Domain Noise Variance for Collaborative Filtering of Stationary Correlated Noise

AU - Mäkinen, Ymir

AU - Azzari, Lucio

AU - Foi, Alessandro

PY - 2019/9

Y1 - 2019/9

N2 - Collaborative filters perform denoising through transform-domain shrinkage of a group of similar blocks extracted from an image. Existing methods for collaborative filtering of stationary correlated noise have all used simple approximations of the transform noise power spectrum adopted from methods which do not employ block grouping. We note the inaccuracies of these approximations and introduce a method for the exact computation and effective approximations of the noise power spectrum. Unlike earlier methods, the calculated noise variances are exact even when noise in one block is correlated with noise in any of the other blocks. We discuss the adoption of the exact noise power spectrum within shrinkage, in similarity testing (block matching), and in aggregation. Extensive experiments support the proposed method over earlier crude approximations used by image denoising filters such as BM3D, demonstrating dramatic improvement in many challenging conditions.

AB - Collaborative filters perform denoising through transform-domain shrinkage of a group of similar blocks extracted from an image. Existing methods for collaborative filtering of stationary correlated noise have all used simple approximations of the transform noise power spectrum adopted from methods which do not employ block grouping. We note the inaccuracies of these approximations and introduce a method for the exact computation and effective approximations of the noise power spectrum. Unlike earlier methods, the calculated noise variances are exact even when noise in one block is correlated with noise in any of the other blocks. We discuss the adoption of the exact noise power spectrum within shrinkage, in similarity testing (block matching), and in aggregation. Extensive experiments support the proposed method over earlier crude approximations used by image denoising filters such as BM3D, demonstrating dramatic improvement in many challenging conditions.

KW - Two dimensional displays

KW - Reactive power

KW - Transforms

KW - Collaboration

KW - Three-dimensional displays

KW - Noise reduction

KW - Noise measurement

KW - Image denoising

KW - correlated noise

KW - collaborative filtering

KW - noise power spectrum

KW - BM3D

U2 - 10.1109/ICIP.2019.8802964

DO - 10.1109/ICIP.2019.8802964

M3 - Conference contribution

SN - 978-1-5386-6250-2

T3 - IEEE International Conference on Image Processing

SP - 185

EP - 189

BT - 2019 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

ER -