GradCSC

Convolutional Sparse Coding in Gradient Domain for MRI Reconstruction

The Code is created based on the method described in the following papers:
[1] J. Xiong , H. Lu , M. Zhang , Q. Liu, Convolutional Sparse Coding in Gradient Domain for MRI Reconstruction,ACTA AUTOMATICA SINICA,43(10):1841-1849, 2017.
Author: J. Xiong , H. Lu , M. Zhang , Q. Liu
Date : 4//2018
Version : 1.0
The code and the algorithm are for non-comercial use only.
Copyright 2018, Department of Electronic Information Engineering, Nanchang University.
GradCSC - Convolutional sparse coding in Gradient domain

Gradientfilters_mri.mat is available at: https://pan.baidu.com/s/1f7tlnFeySu1UNjLtzfVasg.

Visual illustration of learned dictionary/filters.

Left: Learned dictionary by DLMRI. Middle: Learned dictionary by GradDL. Right: Learned filters by GradCSC.

Other Related Projects

• Predual dictionary learning (PDL) / augmented Lagrangian multi-scale dictionary learning(ALM-DL) [Paper] [Code]

• Adaptive dictionary learning in sparse gradient domain for image recovery [Paper] [Code]

• Highly undersampled magnetic resonance image reconstruction using two-level Bregman method with dictionary updating [Paper] [Code]

• Field-of-Experts Filters Guided Tensor Completion [Paper] [Code] [Slide]

• Synthesis-analysis deconvolutional network for compressed sensing [Paper] [Code]

• Sparse and dense hybrid representation via subspace modeling for dynamic MRI [Paper] [Code]

• IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI [Paper] [Code]

• A Comparative Study of CNN-based Super-resolution Methods in MRI Reconstruction and Its Beyond [Paper] [Code]

• Texture variation adaptive image denoising with nonlocal PCA [Paper] [Code]