A Review of Deep Learning for Single Image Super-Resolution

Zhou, Lanfeng; Feng, Shuaijie

doi:10.1109/iciibms46890.2019.8991477

Cited by 5 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there have been some reviews ( Ha et al, 2019 ; Yang et al, 2019 ; Zhang et al, 2019c ; Zhou & Feng, 2019 ; Li et al, 2020 ) focused on deep learning-based image super-resolution. The study by Yang et al (2019) was focused on the deep learning methods for single image super-resolution.…”

Section: Introductionmentioning

confidence: 99%

“… Ha et al (2019) reviewed the state-of-the-art SISR methods and classified them based on the type of framework, i.e., CNN, RNN-CNN-based methods and GAN-based methods. Zhou & Feng (2019) briefly reviewed some of the state-of-the-art SISR methods and provided an introduction of some of the methods without any evaluation of comparison of methods, while Li et al (2020) reviewed the state-of-the-art methods in image SR while emphasizing on the methods based on CNNs and GANs for real-time applications. These review papers did not encompass the domain of super-resolution as a whole, and this paper fills that research gap by providing an overview of both classical and deep learning-based methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive review of deep learning-based single image super-resolution

Bashir

Wang

Khan

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical methods, supervised learning-based methods, unsupervised learning-based methods, and domain-specific SR methods. We also introduce the problem of SR to provide intuition about image quality metrics, available reference datasets, and SR challenges. Deep learning-based approaches of SR are evaluated using a reference dataset. Some of the reviewed state-of-the-art image SR methods include the enhanced deep SR network (EDSR), cycle-in-cycle GAN (CinCGAN), multiscale residual network (MSRN), meta residual dense network (Meta-RDN), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN). Finally, this survey is concluded with future directions and trends in SR and open problems in SR to be addressed by the researchers.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A comprehensive review of deep learning-based single image super-resolution

Bashir

Wang

Khan

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…According to (8), the features and problems of the joint dictionary are as follows: e training object is the set of two image blocks P Y l , X h after feature extraction; feature selection is very important. e gradient features of the rst-and second-order gradients (image texture and edge information) are used here, and it is assumed that the corresponding feature blocks in the two feature spaces have the same sparse representation coe cients.…”

Section: Proposed Joint Dictionary With Loss Function Optimizationmentioning

confidence: 99%

“…Although hardware with better performance can be used to improve image resolution, many researchers prefer to adopt image superresolution reconstruction technology due to cost and technical limitations. Superresolution reconstruction technology refers to the reconstruction of a corresponding high-resolution image from one or more low-resolution images, which is mainly based on methods including interpolation, reconstruction, and learning [6][7][8]. According to [9][10][11], the image interpolation method is to estimate the unknown pixels among the known pixels according to the law of the pixels in a limited area.…”

Section: Introductionmentioning

confidence: 99%

Sparse Dictionary-Based Magnetic Resonance Superresolution Imaging with Joint Loss Function Learning

Liu

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Magnetic resonance image has important application value in disease diagnosis. Due to the particularity of its imaging mechanism, the resolution of hardware imaging needs to be improved by increasing radiation intensity and radiation time. Excess radiation can cause the body to overheat and, in severe cases, inactivate the protein. This problem is expected to be solved by the image superresolution method based on joint dictionary learning, which has good superresolution performance. In the process of dictionary learning, the loss function will directly affect the dictionary performance. The general method only uses the cascade error as the optimization function in dictionary training, and the method does not consider the individual reconstruction error of high- and low-resolution image dictionary. In order to solve the above problem, In this paper, the loss function of dictionary learning is optimized. While ensuring that the coefficients are sufficiently sparse, the high- and low-resolution dictionaries are trained separately to reduce the error generated by the joint high- and low-resolution dictionary block pair and increase the high-resolution reconstruction error. Experiments on neck and ankle MR images show that the proposed algorithm has better superresolution reconstruction performance on ×2 and ×4 compared with bicubic interpolation, nearest neighbor, and original dictionary learning algorithms.

show abstract

“…e Inception structure proposed by Google is a new functional unit, of which the main idea is to improve the convolution kernel to increase the receptive field [17]. In this way, more image information can be learned by the network, and thus the To improve network performance, the easiest way is to add the depth of the network.…”

Section: Research On Multiscale-fusion Modulementioning

confidence: 99%

Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images

Qian

Zhang

et al. 2021

Mobile Information Systems

View full text Add to dashboard Cite

Image denoising and image super-resolution reconstruction are two important techniques for image processing. Deep learning is used to solve the problem of image denoising and super-resolution reconstruction in recent years, and it usually has better results than traditional methods. However, image denoising and super-resolution reconstruction are studied separately by state-of-the-art work. To optimally improve the image resolution, it is necessary to investigate how to integrate these two techniques. In this paper, based on Generative Adversarial Network (GAN), we propose a novel image denoising and super-resolution reconstruction method, i.e., multiscale-fusion GAN (MFGAN), to restore the images interfered by noises. Our contributions reflect in the following three aspects: (1) the combination of image denoising and image super-resolution reconstruction simplifies the process of upsampling and downsampling images during the model learning, avoiding repeated input and output images operations, and improves the efficiency of image processing. (2) Motivated by the Inception structure and introducing a multiscale-fusion strategy, our method is capable of using the multiple convolution kernels with different sizes to expand the receptive field in parallel. (3) The ablation experiments verify the effectiveness of each employed loss measurement in our devised loss function. And our experimental studies demonstrate that the proposed model can effectively expand the receptive field and thus reconstruct images with high resolution and accuracy and that the proposed MFGAN method performs better than a few state-of-the-art methods.

show abstract

A Review of Deep Learning for Single Image Super-Resolution

Cited by 5 publications

References 14 publications

A comprehensive review of deep learning-based single image super-resolution

A comprehensive review of deep learning-based single image super-resolution

Sparse Dictionary-Based Magnetic Resonance Superresolution Imaging with Joint Loss Function Learning

Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images

Contact Info

Product

Resources

About