New Techniques for Preserving Global Structure and Denoising with Low Information Loss in Single-Image Super-Resolution

Bei, Yijie; Alex, Damian,; Hu, Shijia; Menon, Sachit; Ravi, Nikhil; Rudin, Cynthia

doi:10.1109/cvprw.2018.00132

Cited by 25 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For reducing the training difficulty of the network in SR, small scaling factor, SR is performed in the beginning; in the curriculum learning-based SR, the training starts with 2× upsampling, and gradually the following scaling factors , , and so on are generated using the output of previously trained networks. ProSR ( Wang et al, 2018a ) uses the upsampled output of the previous level and linearly trains the next level using the previous one, while ADRSR ( Bei et al, 2018 ) concatenates the HR output of the previous levels and further adds another convolution layer. In CARN ( Ahn, Kang & Sohn, 2018b ), the previously generated image is entirely replaced by the next level generated image, updating the HR image in sequential order.…”

Section: Supervised Super-resolutionmentioning

confidence: 99%

“…In the case of image super-resolution, some of the augmentation techniques are flipping, cropping, angular rotation, skew, and color degradation ( Timofte, Rothe & Van Gool, 2016 ; Lai et al, 2017 ; Lim et al, 2017 ; Tai, Yang & Liu, 2017 ; Han et al, 2018 ). Recoloring the image using channel shuffling in the LR-HR image pair is also used as data augmentation in image SR ( Bei et al, 2018 ).…”

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

100

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%

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

100

View full text Add to dashboard Cite

show abstract

“…It first passes the image through the denoiser prior to branching into main path and skip connection. This is conceptually similar to the denoiser and SR concatenation by Bei et al [20]. One potential limitation of this approach is error propagation: if the denoiser removes information that is relevant to super-resolution, it cannot be recovered afterwards.…”

Section: Methodsmentioning

confidence: 97%

“…Furthermore, deep learning approaches have also been considered to combine denoising with a SR model [19]. The authors in [20] propose cascading a denoiser with a SR model so that the output of the denoiser is fed to the SR network. The pre-network architectural design in our experiments is similar in spirit, but instead of using a fixed convolutional neural network (CNN) denoiser, our design allows for further flexibility regarding the choice of the integrated denoiser.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Architectural Designs for Super-Resolution Of Noisy Images

Villar-Corrales

Schirrmacher

Rieß

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Recent advances in deep learning have led to significant improvements in single image super-resolution (SR) research. However, due to the amplification of noise during the upsampling steps, state-ofthe-art methods often fail at reconstructing high-resolution images from noisy versions of their low-resolution counterparts. However, this is especially important for images from unknown cameras with unseen types of image degradation. In this work, we propose to jointly perform denoising and super-resolution. To this end, we investigate two architectural designs: "in-network" combines both tasks at feature level, while "pre-network" first performs denoising and then super-resolution. Our experiments show that both variants have specific advantages: The in-network design obtains the strongest results when the type of image corruption is aligned in the training and testing dataset, for any choice of denoiser. The prenetwork design exhibits superior performance on unseen types of image corruption, which is a pathological failure case of existing super-resolution models. We hope that these findings help to enable super-resolution also in less constrained scenarios where source camera or imaging conditions are not well controlled. Source code and pretrained models are available at https://github.com/ angelvillar96/super-resolution-noisy-images.

show abstract

“…The network employs motion compensated frames as input and single-image pre-training. In addition, some of the recent challenges on example-based single image SR [14,15,16], through benchmarking and introduction of SR specific datasets promoted several methods for super-resolving images [17,18,19,20,21].…”

Section: Introductionmentioning

confidence: 99%

PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results

Shoeiby

Robles-Kelly

Timofte

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we describe the Perceptual Image Restoration and Manipulation (PIRM) workshop challenge on spectral image superresolution, motivate its structure and conclude on results obtained by the participants. The challenge is one of the first of its kind, aiming at leveraging modern machine learning techniques to achieve spectral image super-resolution. It comprises of two tracks. The first of these (Track 1) is about example-based single spectral image super-resolution. The second one (Track 2) is on colour-guided spectral image super-resolution. In this manner, Track 1 focuses on the problem of super-resolving the spatial resolution of spectral images given training pairs of low and high spatial resolution spectral images. Track 2, on the other hand, aims to leverage the inherently higher spatial resolution of colour (RGB) cameras and the link between spectral and trichromatic images of the scene. The challenge in both tracks is then to recover a super-resolved image making use of low-resolution imagery at the input. We also elaborate upon the methods used by the participants, summarise the results and discuss their rankings.

show abstract

New Techniques for Preserving Global Structure and Denoising with Low Information Loss in Single-Image Super-Resolution

Cited by 25 publications

References 15 publications

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

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

Deep Learning Architectural Designs for Super-Resolution Of Noisy Images

PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results

Contact Info

Product

Resources

About