Skip to search formSkip to main contentSkip to account menu

Nonlocally Centralized Sparse Representation for Image Restoration

The so-called nonlocally centralized sparse representation (NCSR) model is as simple as the standard sparse representation model, and the extensive experiments validate the generality and state-of-the-art performance of the proposed NCSR algorithm.
View on IEEE (opens in a new tab)

Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than many state-of-the-art algorithms in terms of both PSNR and visual perception.
View on IEEE (opens in a new tab)

Two-stage image denoising by principal component analysis with local pixel grouping

View via Publisher (opens in a new tab)

Nonlocal Image Restoration With Bilateral Variance Estimation: A Low-Rank Approach

This paper takes a low-rank approach toward SSC and provides a conceptually simple interpretation from a bilateral variance estimation perspective, namely that singular-value decomposition of similar packed patches can be viewed as pooling both local and nonlocal information for estimating signal variances.
View on IEEE (opens in a new tab)

Compressive Sensing via Nonlocal Low-Rank Regularization

A nonlocal low-rank regularization approach toward exploiting structured sparsity and its application into CS of both photographic and MRI images is proposed and the use of a nonconvex log det as a smooth surrogate function for the rank instead of the convex nuclear norm is proposed.
View on IEEE (opens in a new tab)

Sparse Representation Based Image Interpolation With Nonlocal Autoregressive Modeling

This paper incorporates the image nonlocal self-similarity into SRM for image interpolation, and shows that the NARM-induced sampling matrix is less coherent with the representation dictionary, and consequently makes SRM more effective forimage interpolation.
View on IEEE (opens in a new tab)

Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation

  • W. DongFazuo Fu Xin Li
  • Environmental Science, Computer Science
    IEEE Transactions on Image Processing
  • 22 March 2016
A new hyperspectral image super-resolution method from a low-resolution (LR) image and a HR reference image of the same scene to improve the accuracy of non-negative sparse coding and to exploit the spatial correlation among the learned sparse codes.
View on IEEE (opens in a new tab)

Sparsity-based image denoising via dictionary learning and structural clustering

A double-header l1-optimization problem where the regularization involves both dictionary learning and structural structuring is formulated and a new denoising algorithm built upon clustering-based sparse representation (CSR) is proposed.
View on IEEE (opens in a new tab)

Centralized sparse representation for image restoration

A novel sparse representation model called centralized sparse representation (CSR) is proposed, which achieves convincing improvement over previous state-of-the-art methods on image restoration tasks by exploiting the nonlocal image statistics.
View on IEEE (opens in a new tab)

Denoising Prior Driven Deep Neural Network for Image Restoration

A convolutional neural network (CNN) based denoiser that can exploit the multi-scale redundancies of natural images is proposed, which not only exploits the powerful denoising ability of DNNs, but also leverages the prior of the observation model.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)