The Code is created based on the method described in the following paper:
Learning Multi-Denoising Autoencoding Priors for Image Super-Resolution, Journal of Visual Communication and Image Representation, 2018.
Author: Y. Wang, Q. Liu, H. Zhou, Y. Wang.
Date : 09/2018
Version : 1.0
The code and the algorithm are for non-comercial use only.
Copyright 2018, Department of Electronic Information Engineering, Nanchang University.
MDAEP - Single Image Super-Resolution
Input:
degraded: Observed blurry and noisy input RGB image in range of [0, 255].
up_scale: Up scaling factor.
params: Set of parameters.
params.net: The DAE Network object from matCaffe.
Optional parameters:
map: Initial solution.
params.sigma_net: The standard deviation of the network training noise. default: 11 & 25
params.num_iter: Specifies number of iterations.
params.gamma: Indicates the relative weight between the data term and the prior. default: 28.5
params.mu: The momentum for SGD optimization. default: 0.9
params.alpha the step length in SGD optimization. default: 0.1
-
Multi-Channel and Multi-Model-Based Autoencoding Prior for Grayscale Image Restoration
[Paper] [Code] [Slide] [数学图像联盟会议交流PPT] -
Highly undersampled magnetic resonance imaging reconstruction using autoencoding priors
[Paper] [Code] [Slide] [数学图像联盟会议交流PPT] -
High-dimensional Embedding Network Derived Prior for Compressive Sensing MRI Reconstruction
[Paper] [Code] -
Denoising Auto-encoding Priors in Undecimated Wavelet Domain for MR Image Reconstruction
[Paper] [Paper] [Code] -
Deep Frequency-Recurrent Priors for Inverse Imaging Reconstruction
[Paper] [Code] -
REDAEP: Robust and Enhanced Denoising Autoencoding Prior for Sparse-View CT Reconstruction
[Paper] [Code] [数学图像联盟会议交流PPT]