Poisson Noise Reduction with Non-local PCA

  title={Poisson Noise Reduction with Non-local PCA},
  author={Joseph Salmon and Zachary T. Harmany and Charles-Alban Deledalle and Rebecca M. Willett},
  journal={Journal of Mathematical Imaging and Vision},
Photon-limited imaging arises when the number of photons collected by a sensor array is small relative to the number of detector elements. Photon limitations are an important concern for many applications such as spectral imaging, night vision, nuclear medicine, and astronomy. Typically a Poisson distribution is used to model these observations, and the inherent heteroscedasticity of the data combined with standard noise removal methods yields significant artifacts. This paper introduces a… 
Sparsity-Based Poisson Denoising With Dictionary Learning
The scheme uses a greedy pursuit with boot-strapping-based stopping condition and dictionary learning within the denoising process, and the reconstruction performance is competitive with leading methods in high SNR and achieving state-of-the-art results in cases of low SNR.
A Bayesian Approach to Denoising of Single-Photon Binary Images
A new Bayesian denoising method for binary, single-photon images using a stochastic simulation method to sample the resulting joint posterior distribution and estimate the unknown intensity, as well as the regularization parameters.
Non-local total variation regularization approach for image restoration under a Poisson degradation
ABSTRACT Poisson noise (also known as shot or photon noise) arises due to the lack of information during the image acquisition phase, it is quite common in the field of microscopic or astronomical
Multi-Resolution Aitchison Geometry Image Denoising for Low-Light Photography
This work derives a denoising technique based on an approximate conjugate prior for the latent Aitchison variable that gives rise to an explicit minimum mean squared error estimation, and demonstrates that the difference-log-contrast has wavelet-like properties that correspond well with the human visual system, while being robust to illumination variations.
Logarithmic total variation regularization for cross-validation in photon-limited imaging
A new model is presented that solves for and regularizes the logarithm of the true scene, and focuses on the special case of total variation regularization.
Poisson Denoising of Images Using Deep Neural Networks Inspired by Classical Dictionary Based Algorithms
This work proposes several novel deep learning networks for Poisson denoising based on sparse representation and multiscale analysis principles, and their action and learned parameters can be explained theoretically.
Polarization prior to single-photon counting image denoising.
A novel polarization prior to SPC image denoising is proposed based on the observation that a special polarization SPC (PSPC) image has a higher SNR than the S PC image, which improves the denoised image performance.
Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image
This work explores a sparsity and dictionary learning-based approach and presents a novel self-supervised learning method for single-image denoising where the noise is approximated as a Poisson process, requiring no clean ground-truth data.


Multiscale Analysis of Photon-Limited Astronomical Images
Several multiscale approaches to photon-limited image reconstruction are reviewed, including wavelets combined with variance stabilizing transforms, corrected Haar wavelet transforms, multiplicative multiscales innovations, platelets, and the a trous wavelet transform.
Fast multiresolution photon-limited image reconstruction
  • R. Willett, R. Nowak
  • Computer Science
    2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821)
  • 2004
The techniques described in this paper allow multiscale photon-limited image reconstruction methods to be implemented with significantly less computational complexity than previously possible.
Image denoising with patch based PCA: local versus global
The aim of the present work is to demonstrate that for the task of image denoising, nearly state-of-the-art results can be achieved using orthogonal dictionaries only, provided that they are learned directly from the noisy image.
Multiscale Photon-Limited Spectral Image Reconstruction
Experiments conducted on realistic data sets show that the proposed method can reconstruct the spatial and the spectral inhomogeneities very well even when the observations are extremely photon-limited (i.e., less than 0.1 photon per voxel).
Patch-Based Nonlocal Functional for Denoising Fluorescence Microscopy Image Sequences
A nonparametric regression method for denoising 3-D image sequences acquired via fluorescence microscopy and an original statistical patch-based framework for noise reduction and preservation of space-time discontinuities are presented.
This is SPIRAL-TAP: Sparse Poisson Intensity Reconstruction ALgorithms—Theory and Practice
The optimization formulation considered in this paper uses a penalized negative Poisson log-likelihood objective function with nonnegativity constraints (since Poisson intensities are naturally nonnegative) for estimation of f* from y in an inverse problem setting.
Optimal Inversion of the Generalized Anscombe Transformation for Poisson-Gaussian Noise
The exact unbiased inverse of the Anscombe transformation is introduced and it is demonstrated that this exact inverse leads to state-of-the-art results without any notable increase in the computational complexity compared to the other inverses.
Patch-Based Near-Optimal Image Denoising
This paper proposes a patch-based Wiener filter that exploits patch redundancy for image denoising that is on par or exceeding the current state of the art, both visually and quantitatively.
Optimal Spatial Adaptation for Patch-Based Image Denoising
A novel adaptive and patch-based approach is proposed for image denoising and representation based on a pointwise selection of small image patches of fixed size in the variable neighborhood of each pixel to associate with each pixel the weighted sum of data points within an adaptive neighborhood.
Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising
This work introduces optimal inverses for the Anscombe transformation, in particular the exact unbiased inverse, a maximum likelihood (ML) inverse, and a more sophisticated minimum mean square error (MMSE) inverse.