Persistent Memory Residual Network for Single Image Super Resolution

Chen, Rong; Qu, Yanyun; Zeng, Kun; Guo, Jinkang; Li, Cuihua; Xie, Yuan

doi:10.1109/cvprw.2018.00125

Cited by 17 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Batch normalization is a technique that performs well in computer vision tasks and reduces the overall runtime of the training, and enhances the performance; however, in SR batch normalization proved to be sub-optimal ( Lim et al, 2017 ; Wang et al, 2018a ; Chen et al, 2018a ). In this regard, normalization techniques for super-resolution should be explored further.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

“…Thus, there is a lack of flexibility in the network; hence, Lim et al (2017) removed batch normalization and used the additional memory to design a large model with superior performance compared to the BN-based network. Other studies Wang et al (2019c) , Wang et al (2018a) and Chen et al (2018a) also implemented this technique to achieve marginally better performance.…”

Section: Supervised Super-resolutionmentioning

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: Discussion and Future Directionsmentioning

confidence: 99%

Section: Supervised Super-resolutionmentioning

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

“…In each group, it is further split into models trained using L2 loss function and 9 L1 loss function. SR models in the 'Bicubic' group include the SRCNN [28], VDSR [29], DRRN [54], MemNet [55], DnCNN [56], LapSRN [38], ZSSR [57], CARN [58], SRRAM [59]. In the 'Learned' group, we compare the CAR model with two recent state-of-the-art image downscaling models trained jointly with deep SR models, i.e., the CNN-CR→CNN-SR [4] model and the TAD→TAU model [21].…”

Section: Comparison With Public Benchmark Sr Resultsmentioning

confidence: 99%

Learned Image Downscaling for Upscaling Using Content Adaptive Resampler

Sun

Chen

2020

IEEE Trans. on Image Process.

146

View full text Add to dashboard Cite

Deep convolutional neural network based image super-resolution (SR) models have shown superior performance in recovering the underlying high resolution (HR) images from low resolution (LR) images obtained from the predefined downscaling methods. In this paper we propose a learned image downscaling method based on content adaptive resampler (CAR) with consideration on the upscaling process. The proposed resampler network generates content adaptive image resampling kernels that are applied to the original HR input to generate pixels on the downscaled image. Moreover, a differentiable upscaling (SR) module is employed to upscale the LR result into its underlying HR counterpart. By back-propagating the reconstruction error down to the original HR input across the entire framework to adjust model parameters, the proposed framework achieves a new state-of-the-art SR performance through upscaling guided image resamplers which adaptively preserve detailed information that is essential to the upscaling. Experimental results indicate that the quality of the generated LR image is comparable to that of the traditional interpolation based method, but the significant SR performance gain is achieved by deep SR models trained jointly with the CAR model. The code is publicly available on: URL https://github.com/sunwj/CAR.

show abstract

“…In Generator, LR images are input to the network followed by one Conv layer for extracting shallow features. Then four memory residual (MR) blocks are applied for improving image quality which help to form persistent memory and improve the feature selection ability of model like MemEDSR [26]. Each MR block consists of four ResBlocks and a gate unit.…”

Section: Mr-srganmentioning

confidence: 99%

Bi-GANs-ST for Perceptual Image Super-Resolution

Luo

Chen

Xie

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Image quality measurement is a critical problem for image super-resolution (SR) algorithms. Usually, they are evaluated by some well-known objective metrics, e.g., PSNR and SSIM, but these indices cannot provide suitable results in accordance with the perception of human being. Recently, a more reasonable perception measurement has been proposed in [1], which is also adopted by the PIRM-SR 2018 challenge. In this paper, motivated by [1], we aim to generate a high-quality SR result which balances between the two indices, i.e., the perception index and root-mean-square error (RMSE). To do so, we design a new deep SR framework, dubbed Bi-GANs-ST, by integrating two complementary generative adversarial networks (GAN) branches. One is memory residual SRGAN (MR-SRGAN), which emphasizes on improving the objective performance, such as reducing the RMSE. The other is weight perception SRGAN (WP-SRGAN), which obtains the result that favors better subjective perception via a two-stage adversarial training mechanism. Then, to produce final result with excellent perception scores and RMSE, we use soft-thresholding method to merge the results generated by the two GANs. Our method performs well on the perceptual image super-resolution task of the PIRM 2018 challenge. Experimental results on five benchmarks show that our proposal achieves highly competent performance compared with other state-of-the-art methods.

show abstract

Persistent Memory Residual Network for Single Image Super Resolution

Cited by 17 publications

References 16 publications

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

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

Learned Image Downscaling for Upscaling Using Content Adaptive Resampler

Bi-GANs-ST for Perceptual Image Super-Resolution

Contact Info

Product

Resources

About