Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network Article Swipe

MAKE IMPACT

Yudong Liang , Ze Yang , Kai Zhang , Yihui He , Jinjun Wang , Nanning Zheng · YOU? · · 2017 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1703.08173

Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numbers of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. In addition, the skip connections have naturally centered the activation which led to better performance. To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed. In particular, a strategy of gradually varying the shape of network has been proposed for residual network. Different residual architectures for image super-resolution have also been compared. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-the-art PSNR and SSIM results for single image super-resolution but also produce visually pleasant results. This paper has extended the mmm 2017 oral conference paper with a considerable new analyses and more experiments especially from the perspective of centering activations and ensemble behaviors of residual network.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/1703.08173

PDF

https://arxiv.org/pdf/1703.08173

OA Status

green

Cited By

13

References

37

Related Works

10

OpenAlex ID

https://openalex.org/W2773653677

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W2773653677

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.1703.08173

Digital Object Identifier

Title

Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2017

Year of publication

Publication date

2017-03-23

Full publication date if available

Authors

Yudong Liang, Ze Yang, Kai Zhang, Yihui He, Jinjun Wang, Nanning Zheng

List of authors in order

Landing page

https://arxiv.org/abs/1703.08173

Publisher landing page

PDF URL

https://arxiv.org/pdf/1703.08173

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/1703.08173

Direct OA link when available

Concepts

Convolutional neural network, Residual, Computer science, Superresolution, Artificial intelligence, Image (mathematics), Resolution (logic), Computer vision, Pattern recognition (psychology), Algorithm

Top concepts (fields/topics) attached by OpenAlex

Cited by

13

Total citation count in OpenAlex

Citations by year (recent)

2023: 1, 2021: 2, 2020: 2, 2019: 4, 2018: 4

Per-year citation counts (last 5 years)

References (count)

37

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload