Wavelet-based residual attention network for image super-resolution

Xue, Shengke; Qiu, Wenyuan; Liu, Fan; Jin, Xinyu

doi:10.1016/j.neucom.2019.11.044

Cited by 50 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WT was used in SR to generate the residuals of the HR sub-bands using the sub-bands of the interpolated LR wavelet. Using the WT, the LR image is decomposed, while the inverse WT provides the reconstruction of the HR image in SR. Other examples of WT based SR are Wavelet-based residual attention network (WRAN) ( Xue et al, 2020 ), multi-level wavelet CNN (MWCNN) ( Liu et al, 2018b ) and ( Ma et al, 2019 ); these approaches used a hybrid approach by combining WT with other learning methods to improve the overall performance.…”

Section: Supervised Super-resolutionmentioning

confidence: 99%

“…We show our gratitude to the authors of all referred research studies for sharing results, especially to the authors of Kim, Lee & Lee (2016b) , Ledig et al (2017) , Dong, Loy & Tang (2016) , Lai et al (2017) , Haris, Shakhnarovich & Ukita (2018) , Hu et al (2019) , Tai, Yang & Liu (2017) , Tai et al (2017) , Li et al (2018) , Lim et al (2017) , Zhang et al (2018a) , Dai et al (2019) , Xue et al (2020) and Caballero et al (2017) .…”

mentioning

confidence: 94%

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: Supervised Super-resolutionmentioning

confidence: 99%

mentioning

confidence: 94%

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

“…Many deep learningbased algorithms have been used for image classification, 17,18 segmentation, 19,20 detection, 21 and denoising. [22][23][24][25] In recent years, machine learning, especially deep learning, has been widely used in the development of tomographic reconstruction techniques. 26 Wang et al 27 reported that radiology would be significantly improved by introducing machine learning in the next 5 years.…”

Section: Introductionmentioning

confidence: 99%

Incorporation of residual attention modules into two neural networks for low‐dose CT denoising

Mei

Duan

et al. 2021

Medical Physics

View full text Add to dashboard Cite

Purpose The low‐dose computed tomography (CT) imaging can reduce the damage caused by x‐ray radiation to the human body. However, low‐dose CT images have a different degree of artifacts than conventional CT images, and their resolution is lower than that of conventional CT images, which can affect disease diagnosis by clinicians. Therefore, methods for noise‐level reduction and resolution improvement in low‐dose CT images have inevitably become a research hotspot in the field of low‐dose CT imaging. Methods In this paper, residual attention modules (RAMs) are incorporated into the residual encoder–decoder convolutional neural network (RED‐CNN) and generative adversarial network with Wasserstein distance (WGAN) to learn features that are beneficial to improving the performances of denoising networks, and developed models are denoted as RED‐CNN‐RAM and WGAN‐RAM, respectively. In detail, RAM is composed of a multi‐scale convolution module and an attention module built on the residual network architecture, where the attention module consists of a channel attention module and a spatial attention module. The residual network architecture solves the problem of network degradation with increased network depth. The function of the attention module is to learn which features are beneficial to reduce the noise level of low‐dose CT images to reduce the loss of detail in the final denoising images, which is also the key point of the proposed algorithms. Results To develop a robust network for low‐dose CT image denoising, multidose‐level torso phantom images provided by a cooperating equipment vendor are used to train the network, which can improve the network’s adaptability to clinical application. In addition, a clinical dataset is used to test the network’s migration capabilities and clinical applicability. The experimental results demonstrate that these proposed networks can effectively remove noise and artifacts from multidose CT scans. Subjective and objective analyses of multiple groups of comparison experiments show that the proposed networks achieve good noise suppression performance while preserving the image texture details. Conclusion In this study, two deep learning network models are developed using multidose‐level CT images acquired from a commercial spiral CT scanner. The two network models can reduce and even remove streaking artifacts, and noise from low‐dose CT images confirms the effectiveness of the proposed algorithms.

show abstract

“…Therefore, we perform the recovery of high frequency subbands LH, HL, and HH different from that of LL subband. We use a variant of inception network [4], [32] as the basic module, named multi-kernel convolutional module (Multi-Kernel Conv Module in Fig. 2), and connect the modules by weakly dense connection [16], [26].…”

Section: B Subband Adaptive Deblockingmentioning

confidence: 99%

“…2), and connect the modules by weakly dense connection [16], [26]. The inception network [24], [32] is an effective structure that can adaptively learn image features of different scales. The network structure of the multi-kernel convolutional module is shown in Fig.…”

Section: B Subband Adaptive Deblockingmentioning

confidence: 99%

Subband Adaptive Image Deblocking Using Wavelet Based Convolutional Neural Networks

Jung

Xie

2021

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose subband adaptive image deblocking using wavelet based convolutional neural networks (CNNs). We build wavelet based CNNs for image deblocking to achieve subband adaptive reconstruction. First, we perform subband adaptive processing after the discrete wavelet transform (DWT) on the input image. For low frequency subband (LL), we use a simple and effective shallow CNN to restore the low frequency component, while for high frequency subbands (LH, HL, and HH) we utilize multi-kernel convolution to capture multiscale features and restore sparse high frequency components. Then, we conduct mixed convolution of dilated convolution and standard convolution to expand the receptive field while introducing channel and spatial attentions to adjust the proportion of different subbands and spatial coordinates. Various experiments on Classic5 and LIVE1 datasets show that the proposed method successfully recovers sharp edges and clear textures in highly compressed images while removing compression artifacts such as blocking and banding. Moreover, the proposed method achieves comparable state-of-the-art performance on compression artifact removal in terms of both visual quality and quantitative measurements.INDEX TERMS Image deblocking, compression, convolutional neural network, wavelet, subband adaptive.

show abstract

Wavelet-based residual attention network for image super-resolution

Cited by 50 publications

References 18 publications

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

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

Incorporation of residual attention modules into two neural networks for low‐dose CT denoising

Subband Adaptive Image Deblocking Using Wavelet Based Convolutional Neural Networks

Contact Info

Product

Resources

About