Multiscale KSVD Denoising

Description

Multiscale KSVD for :

– Denoising
– InPainting
– Demosaicing
– Video Denoising
– Video InPainting
– Video Demosaicing

Introduction
– This software is parallel implementation of the three following papers,

-# M. Elad and M. Aharon, “Image Denoising Via Sparse and Redundant representations over Learned Dictionaries”, the
IEEE Trans. on Image Processing, Vol. 15, no. 12, pp. 3736-3745, December 2006.

-# J. Mairal, M. Elad, and G. Sapiro, “Sparse Representation for Color Image Restoration”, Submitted to IEEE Trans. on Image  Processing.
http://www.ima.umn.edu/preprints/oct2006/2139.pdf

-# J. Mairal, G. Sapiro and M. Elad, “Multiscale sparse image representation with learned dictionaries”. submitted.
http://www.ima.umn.edu/preprints/jan2007/2152.pdf

– The first paper describes the first K-SVD denoising algorithm.
– The second paper describes the inpainting/denoising/demosaicing for color image restoration.
– The last paper presents a multiscale version of the first denoising algorithm as well as some algorithmic improvements.

Denoising using autoencoders in TensorFlow

Image denoising