Variance Stabilization for Noisy+Estimate Combination in Iterative Poisson Denoising

Research output: Contribution to journal › Article › Scientific › peer-review

Standard

Variance Stabilization for Noisy+Estimate Combination in Iterative Poisson Denoising. / Azzari, Lucio ; Foi, Alessandro.

In: IEEE Signal Processing Letters, Vol. 23, No. 8, 01.08.2016, p. 1086-1090.

Research output: Contribution to journal › Article › Scientific › peer-review

Bibtex - Download

@article{3e63a2acd3034c05bff1eabd823e8c9a,

title = "Variance Stabilization for Noisy+Estimate Combination in Iterative Poisson Denoising",

abstract = "We denoise Poisson images with an iterative algorithm that progressively improves the effectiveness of variance-stabilizing transformations (VST) for Gaussian denoising filters. At each iteration, a combination of the Poisson observations with the denoised estimate from the previous iteration is treated as scaled Poisson data and filtered through a VST scheme. Due to the slight mismatch between a true scaled Poisson distribution and this combination, a special exact unbiased inverse is designed. We present an implementation of this approach based on the BM3D Gaussian denoising filter. With a computational cost at worst twice that of the noniterative scheme, the proposed algorithm provides significantly better quality, particularly at low signal-to-noise ratio, outperforming much costlier state-of-the-art alternatives.",

keywords = "Anscombe transformation, image denoising, iterative filtering, photon-limited imaging, Poisson noise",

author = "Lucio Azzari and Alessandro Foi",

year = "2016",

month = "8",

day = "1",

doi = "10.1109/LSP.2016.2580600",

language = "English",

volume = "23",

pages = "1086--1090",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers",

number = "8",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Variance Stabilization for Noisy+Estimate Combination in Iterative Poisson Denoising

AU - Azzari, Lucio

AU - Foi, Alessandro

PY - 2016/8/1

Y1 - 2016/8/1

N2 - We denoise Poisson images with an iterative algorithm that progressively improves the effectiveness of variance-stabilizing transformations (VST) for Gaussian denoising filters. At each iteration, a combination of the Poisson observations with the denoised estimate from the previous iteration is treated as scaled Poisson data and filtered through a VST scheme. Due to the slight mismatch between a true scaled Poisson distribution and this combination, a special exact unbiased inverse is designed. We present an implementation of this approach based on the BM3D Gaussian denoising filter. With a computational cost at worst twice that of the noniterative scheme, the proposed algorithm provides significantly better quality, particularly at low signal-to-noise ratio, outperforming much costlier state-of-the-art alternatives.

AB - We denoise Poisson images with an iterative algorithm that progressively improves the effectiveness of variance-stabilizing transformations (VST) for Gaussian denoising filters. At each iteration, a combination of the Poisson observations with the denoised estimate from the previous iteration is treated as scaled Poisson data and filtered through a VST scheme. Due to the slight mismatch between a true scaled Poisson distribution and this combination, a special exact unbiased inverse is designed. We present an implementation of this approach based on the BM3D Gaussian denoising filter. With a computational cost at worst twice that of the noniterative scheme, the proposed algorithm provides significantly better quality, particularly at low signal-to-noise ratio, outperforming much costlier state-of-the-art alternatives.

KW - Anscombe transformation

KW - image denoising

KW - iterative filtering

KW - photon-limited imaging

KW - Poisson noise

U2 - 10.1109/LSP.2016.2580600

DO - 10.1109/LSP.2016.2580600

M3 - Article

VL - 23

SP - 1086

EP - 1090

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 8

ER -

TUTCRIS Research Portal