research-article

Single Image Super Resolution Reconstruction Based on the Combination of Residual Encoding-Decoding Structure and GAN

Authors:

YingHua LiAuthors Info & Claims

AIPR '21: Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

Pages 144 - 150

https://doi.org/10.1145/3488933.3488989

Published: 25 February 2022 Publication History

Abstract

In recent years, methods based on deep neural networks have achieved excellent performance in the field of image super-resolution. In order to generate more realistic images, based on the super-resolution generative adversarial network (SRGAN), this paper proposes a single-image super-resolution reconstruction model combining residual encoding-decoding structure and generative adversarial network. To further improve the visual perception effect, the encoding-decoding module with residual groups is used as a generator network. Compared with residual blocks, the encoding-decoding module uses a larger receptive field to obtain more effective features and enhance the ability to obtain contextual information of the input image. The residual group is compromised of multiple residual channel attention modules connected with the residual of a single convolutional layer. It can refine the eigenvalues of the network layer and improve the ability to obtain high-frequency detail information in an image. Experimental results have proved that our method is better than existing ones in both objective and subjective visual effects, and the texture details of the reconstructed high resolution image are more realistic.

References

[1]

Rasti P, Uiboupin T, Escalera S, and Anbarjafari G. 2016. Convolutional neural network super resolution for face recognition in surveillance monitoring. In Proceedings of the International Conference on Articulated Motion and Deformable Objects. Palma de Mallorca, Spain, 175-184. https://doi.org/10.1007/978-3-319-41778-3_18

[2]

Pengrui Wang, Haopeng Zhang, Feng Zhou, and Zhiguo Jiang. 2019. Unsupervised Remote Sensing Image Super-Resolution Using Cycle CNN. In Proceedings of the International Geoscience and Remote Sensing Symposium (IGARSS). Yokohama, Japan, 3117-3120. https://doi.org/10.1109/IGARSS.2019.8898648

[3]

Jianan Li, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng, and Shuicheng Yan. 2017. Perceptual generative adversarial networks for small object detection. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI,1951-1959. https://doi.org/10.1109/CVPR.2017.211

[4]

Yeon Ju Lee and Jungho Yoon. 2010. Nonlinear image upsampling method based on radial basis function interpolation. IEEE Trans. Image Process. 19, 10 (October 2010), 2682-2692. https://doi.org/10.1109/TIP.2010.2050108

Digital Library

[5]

Y. Romano, M. Protter, and M. Elad. 2014. Single image interpolation via adaptive nonlocal sparsity-based modeling. IEEE Trans. Image Process. 23, 7 (July 2014), 3085-3098. https://doi.org/10.1109/TIP.2014.2325774

[6]

Shengyang Dai, Mei Han, Ying Wu, and Yihong Gong. 2007. Bilateral back-projection for single image super resolution. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo. Beijing, China, 1039-1042. https://doi.org/10.1109/ICME.2007.4284831

[7]

Jianchao Yang, John Wright, Thomas S. Huang, and Yi Ma. 2010. Image super-resolution via sparse representation. IEEE Trans. Image Process. 19,11(November 2010), 2861-2873. https://doi.org/10.1109/TIP.2010.2050625

Digital Library

[8]

Jianchao Yang, Zhaowen Wang, Zhe Lin, Scott Cohen, and Thomas Huang. 2012. Coupled dictionary training for image super-resolution. IEEE Trans. Image Process. 21, 8(August 2012), 3467-3478. https://doi.org/10.1109/TIP.2012.2192127

Digital Library

[9]

Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2014. Learning a deep convolutional network for image super-resolution. [C]// European Conference on Computer Vision. 8692, (September 2014),184-199. https://doi.org/10.1007/978-3-319-10593-2_13

[10]

Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 1646-1654. https://doi.org/10.1109/CVPR.2016.182

[11]

Dong, C, Loy, C.C, Tang, X. 2016. Accelerating the super-resolution convolutional neural network. European Conference on Computer Vision. 9906, (September 2016), 391-407. https://doi.org/10.1007/978-3-319-46475-6_25

[12]

Wenzhe Shi, Jose Caballero, Ferenc Huszár, and 2016. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 1874-1883. https://doi.org/10.1109/CVPR.2016.207

[13]

J. Kim, J. K. Lee, and K. M. Lee. 2016. Deeply-recursive convolutional network for image super-resolution. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 1637-1645. https://doi.org/10.1109/CVPR.2016.181

[14]

Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, and Wei Wu. 2019. Feedback network for image super-resolution. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Long Beach, CA, 3862-3871. https://doi.org/10.1109/CVPR.2019.00399

[15]

Ying Tai, Jian Yang, and Xiaoming Liu. 2017. Image super-resolution via deep recursive residual network. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, 2790-2798. https://doi.org/10.1109/CVPR.2017.298

[16]

Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. 2017. Densely connected convolutional networks. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2261-2269. https://doi.org/10.1109/CVPR.2017.243

[17]

Tong Tong, Gen Li, Xiejie Liu, and Qinquan Gao. 2017. Image Super-Resolution Using Dense Skip Connections. In Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy, 4809-4817. https://doi.org/10.1109/ICCV.2017.514

[18]

Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. 2018. Residual Dense Network for Image Super-Resolution. In Proceedings of the Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, 2472-2481. https://doi.org/10.1109/CVPR.2018.00262

[19]

D. Jang and R. Park. 2019. DenseNet With Deep Residual Channel-Attention Blocks for Single Image Super Resolution. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Long Beach, CA, 1795-1803.

[20]

Goodfellow I J, Pouget-Abadie J, Mirza M, Bing X, and Bengio Y. 2014. Generative Adversarial Nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems. 2 (December 2014), 2672–2680.

[21]

L. J. Ratliff, S. A. Burden, and S. S. Sastry. 2013. Characterization and computation of local Nash equilibria in continuous games. In 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton). Monticello, IL, 917-924. https://doi.org/10.1109/Allerton.2013.6736623

[22]

Christian Ledig, Lucas Theis, Ferenc Huszár, and 2017. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 105-114. https://doi.org/ 10.1109/CVPR.2017.19

[23]

Xiaojiao Mao, Chunhua Shen, and Yubin Yang. 2016. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In Advances in Neural Information Processing Systems. 29, (March 2016), 2802–2810.

[24]

Guoan Cheng, Ai Matsune, Qiuyu Li, Leilei Zhu, Huaijuan Zang and Shu Zhan. 2019. Encoder-Decoder Residual Network for Real Super-Resolution. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, Long Beach, CA, 2169-2178. https://doi.org/10.1109/CVPRW.2019.00270

[25]

Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. 2018. Image super-resolution using very deep residual channel attention networks. In Proceedings of European Conference on Computer Vision. Munich, Germany, 294–310. https://doi.org/10.1007/978-3-030-01234-2_18

Digital Library

[26]

Radu Timofte, Eirikur Agustsson, Luc Van Gool, and 2017. Ntire 2017 challenge on single image super-resolution: Methods and results. In Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, Honolulu, HI, USA, 1110-1121

[27]

M Bevilacqua, A Roumy, C Guillemot, and A Morel. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In Proceedings of the Electronic Proceedings of the British Machine Vision Conference. https://doi.org/10.5244/C.26.135

[28]

R Zeyde, M Elad, and M Protter. 2019. On single image scale-up using sparse-representations. In International Conference on Curves and Surfaces. Springer, Berlin, Heidelberg, 711-730. https://doi.org/10.1007/978-3-642-27413-8_47

Digital Library

[29]

D. Martin, C. Fowlkes, D. Tal, and J. Malik. 2001. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proceedings Eighth IEEE International Conference on Computer Vision. Vancouver, BC, Canada, 416-423

[30]

Jia Bin Huang, Abhishek Singh, and Narendra Ahuja. 2015. Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, Boston, MA, USA, 5197-5206

Cited By

Nayak AVenugopala PAshwini B(2024)A Systematic Review on Generative Adversarial Network (GAN): Challenges and Future DirectionsArchives of Computational Methods in Engineering10.1007/s11831-024-10119-131:8(4739-4772)Online publication date: 14-May-2024
https://doi.org/10.1007/s11831-024-10119-1

Index Terms

Single Image Super Resolution Reconstruction Based on the Combination of Residual Encoding-Decoding Structure and GAN
1. Computing methodologies

Index terms have been assigned to the content through auto-classification.

Recommendations

Degradation Reconstruction Loss: A Perceptual-Oriented Super-Resolution Framework for Multi-downsampling Degradations
Image and Graphics
Abstract
Recent years have witnessed the great success of deep learning-based single image super-resolution (SISR) methods. However, most of the existing SR methods assume that low-resolution (LR) images are purely bicubic downsampled from high-resolution (...
Single image super-resolution reconstruction based on multi-scale feature mapping adversarial network
Highlights
- The encoder-decoder structure efficiently enlarges the receptive filed.
- Multi-...
Abstract
Single image super-resolution (SISR) aims to reconstruct a high-resolution image from a degraded low-resolution image. In recent years, the super-resolution methods based on convolutional neural network (CNN) have achieved promising ...
Graphical abstract

Display Omitted
Single-image super-resolution with multilevel residual attention network
Abstract
Recently, a great variety of image super-resolution (SR) algorithms based on convolutional neural network (CNN) have been proposed and achieved significant improvement. But how to restore more high-frequency details such as edges and textures is ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

AIPR '21: Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

September 2021

715 pages

ISBN:9781450384087

DOI:10.1145/3488933

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 February 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

AIPR 2021

AIPR 2021: 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

September 24 - 26, 2021

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
54
Total Downloads

Downloads (Last 12 months)9
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Nayak AVenugopala PAshwini B(2024)A Systematic Review on Generative Adversarial Network (GAN): Challenges and Future DirectionsArchives of Computational Methods in Engineering10.1007/s11831-024-10119-131:8(4739-4772)Online publication date: 14-May-2024
https://doi.org/10.1007/s11831-024-10119-1

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten