EPLL: An Image Denoising Method Using a Gaussian Mixture Model Learned on a Large Set of Patches
Samuel Hurault, Thibaud Ehret, Pablo Arias
→ BibTeX
@article{ipol.2018.242,
    title   = {{EPLL: An Image Denoising Method Using a Gaussian Mixture Model Learned on a Large Set of Patches}},
    author  = {Hurault, Samuel and Ehret, Thibaud and Arias, Pablo},
    journal = {{Image Processing On Line}},
    volume  = {8},
    pages   = {465--489},
    year    = {2018},
    doi     = {10.5201/ipol.2018.242},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2018.242}}
published
2018-12-23
reference
Samuel Hurault, Thibaud Ehret, and Pablo Arias, EPLL: An Image Denoising Method Using a Gaussian Mixture Model Learned on a Large Set of Patches, Image Processing On Line, 8 (2018), pp. 465–489. https://doi.org/10.5201/ipol.2018.242

Communicated by Pablo Arias
Demo edited by Thibaud Ehret

Abstract

The Expected Patch Log-Likelihood method, introduced by Zoran and Weiss, allows for whole image restoration using a patch-based prior (in the likelihood sense) for which a maximum a-posteriori (MAP) estimate can be calculated. The prior used is a Gaussian mixture model whose parameters are learned from a dataset of natural images. This article presents a detailed implementation of the algorithm in the context of denoising of images contaminated with white additive Gaussian noise. In addition, two possible extensions of the algorithm to handle color images are compared.

Download