Single image super-resolution using regularization of non-local steering kernel regression

Zhang, Kaibing; Gao, Xinbo; Li, Jie; Xia, Huang

doi:10.1016/j.sigpro.2015.11.025

Cited by 27 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As multi-scale pyramid is built using up scaling factor of 2 , to achieve scale factors of 2,4,8 is quite time consuming task and actually there are no prominent variations in the image structure with such small step size. Average PSNR of [19] when compared with existing SR methods like [20], [21] is improved on four benchmark datasets viz. Set5, Set14, BSD500 & UIUC, but PSNR of [22] was found to be more.…”

Section: A Techniques For Single Image Super Resolution (Sisr)mentioning

confidence: 99%

A New Optimized Recurrent Feedback Deep Convolutional Neural Net for Image Super Resolution

Borse*¹,

Patil²

2019

IJRTE

View full text Add to dashboard Cite

Now-a-days many applications dealing with visual content need to access underlying details in the image or video of interest. For instance, detailing is required to take life critical decisions for further action plans by a doctor. Clarity and structural information are some of the aspects of detailing. It can be achieved by cost effective software solution like super resolution reconstruction of an image. Super resolution (SR) deals in increasing resolution of an image to make it more clear and valid for use. Many SR techniques exist with variable goals to achieve. With this intension a new technique for preserving structural information in the reconstruction process is proposed. The system extends a deep convolution neural network by adding a new optimization layer at the end of network activation layer. This new layer maintains permissible error threshold in the acquired signal and tries to improve the signal by feeding back latest reconstructed frame. The proposed system shows noticeable improvement in structural similarity of reconstructed images as compared with the ground truth.

show abstract

Section: A Techniques For Single Image Super Resolution (Sisr)mentioning

confidence: 99%

A New Optimized Recurrent Feedback Deep Convolutional Neural Net for Image Super Resolution

Borse*¹,

Patil²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Traditional TV regularisation assumes that most of the natural image is smooth; hence, the TV modulus value of a natural image should be small. The traditional model of TV regularisation is as follows [42–44]:

{\hat{H}}^{normalt} = arg min_{{bold-italicH}^{normalt}} (}{, \int (||, \nabla {bold-italicH}^{normalt}) + \frac{λ}{2} {(∥∥, normalΨ {bold-italicH}^{normalt} - {bold-italicL}^{normalt})}_{2}^{2})

where

{\hat{H}}^{normalt}

is the reconstructed HR image;

{bold-italicH}^{normalt}

is the HR image to be optimised;

λ

is the Lagrange multiplier;

{bold-italicL}^{normalt}

is the original LR image; and

Y

is a degradation matrix.…”

Section: Related Workmentioning

confidence: 99%

Discarding jagged artefacts in image upscaling with total variation regularisation

Fan

et al. 2019

IET image process

View full text Add to dashboard Cite

Image upscaling is needed in many areas. There are two types of methods: methods based on a simple hypothesis and methods based on machine learning. Most of the machine learning‐based methods have disadvantages: no support is provided for a variety of upscaling factors, a training process with a high time cost is required, and a large amount of storage space and high‐end equipment are required. To avoid the disadvantages of machine learning, upscaling images with a simple hypothesis is a promising strategy but simple hypothesis always produces jaggy artifacts. The authors propose a new method to remove these jagged artifacts. They consider an edge in an image as a deformed curve. Removing jagged artefacts is considered equivalent to shortening the full arc length of a curve. By optimising the regularization model, the severity of the artifacts decreases as the number of iterations increases. They compare nine existing methods on the Set5, Set14, and Urban100 datasets. Without using any external data, the proposed algorithm has high visual quality, has few jagged artefacts and performs similarly to very recent state‐of‐the‐art deep convolutional network‐based approaches. Compared to other methods without external data, the proposed algorithm balances the quality and time cost well.

show abstract

“…For example, kernel based regression [26], [27] was used to learn nonlinear regression functions for mapping lowresolution feature vectors to high-resolution feature vectors in [11], [28]. Steering kernel regression was used by [29], [30]. Wang et al [31] used active-sampling Gaussian process regression for super-resolution.…”

Section: A Brief Review On Single-image Super-resolutionmentioning

confidence: 99%

Pairwise Operator Learning for Patch-Based Single-Image Super-Resolution

Tang

Shao

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Motivated by the fact that image patches could be inherently represented by matrices, single-image super-resolution is treated as a problem of learning regression operators in a matrix space in this paper. The regression operators that map low-resolution image patches to high-resolution image patches are generally defined by left and right multiplication operators. The pairwise operators are respectively used to extract the raw and column information of low-resolution image patches for recovering high-resolution estimations. The patch based regression algorithm possesses three favorable properties. Firstly, the proposed super-resolution algorithm is efficient during both training and testing, because image patches are treated as matrices. Secondly, the data storage requirement of the optimal pairwise operator is far less than most popular single-image super-resolution algorithms because only two small sized matrices need to be stored. Lastly, the super-resolution performance is competitive with most popular single-image super-resolution algorithms because both raw and column information of image patches is considered. Experimental results show the efficiency and effectiveness of the proposed patch-based single-image superresolution algorithm. IndexTerms-Single-image super-resolution, matrix space, matrix-value operator regression, left and right multiplication operators.

show abstract

Single image super-resolution using regularization of non-local steering kernel regression

Cited by 27 publications

References 28 publications

A New Optimized Recurrent Feedback Deep Convolutional Neural Net for Image Super Resolution

A New Optimized Recurrent Feedback Deep Convolutional Neural Net for Image Super Resolution

Discarding jagged artefacts in image upscaling with total variation regularisation

Pairwise Operator Learning for Patch-Based Single-Image Super-Resolution

Contact Info

Product

Resources

About