Improved Super-resolution Network based on SRCNN
Authors: 
Bin Yang, Kai Xie, Hongbo Pan, and Yuyan ChenAuthors Info & Claims
Bin Yang, Kai Xie, Hongbo Pan, and Yuyan ChenAuthors Info & ClaimsDecember 2021
Article No.: 60, Pages 1 - 6
Abstract
The process of recovering high-resolution images from one or more degraded low-resolution images is known as super-resolution reconstruction. The present super-resolution (SR) deep learning technique has certain limitations, because the deeper the network layer, the higher the training cost and time consumption. This paper, based on SRCNN, revamped the three-step reconstructed process of SRCNN by including VGG and residual ideas. Enhancing its network structure by utilizing subpixel convolution approach which can replace the step of image preprocessing and upscale in SRCNN algorithm. When comparing the reconstructed pictures of Set5, Set14, BSDS100, Urban100, and Manga109 data sets, the revised SRCNN structure outperforms the original SRCNN by 1.1dB in Peak Signal to Noise Ratio (PSNR) and 0.026 in structural similarity (SSIM). When compared to other popular SR network except for SRCNN, the improved reconstructed network has fewer network layers, is easier to train, and produces higher reconstructed image quality than the original SRCNN.
References
[1]
Harris J L. Diffraction and resolving power[J]. Journal of the Optical Society of America (JOSA), 1964, 54(7): 931-936.
[2]
X. -g. Zhang, "A New Kind of Super-Resolution Reconstruction Algorithm Based on the ICM and the Bicubic Interpolation," 2008 International Symposium on Intelligent Information Technology Application Workshops, 2008, pp. 817-82.
[3]
H.P. Xie, K.L. Xie, H.T. Yang. “Research progress of image super-resolution methods”. Computer Engineering and Applications,2020,56(19). pp:34-41
[4]
C. Dong, C. C. Loy, K. He, and X. Tang, "Learning a Deep Convolutional Network for Image Super-Resolution," Computer Vision – ECCV 2014, pp. 184-199
[5]
Dong C, Loy CC, He K, Tang X. Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans Pattern Anal Mach Intell. 2016 Feb;38(2):295-307. 26761735
[6]
Dong C., Loy C.C., Tang X. “Accelerating the Super-Resolution Convolutional Neural Network. Computer Vision” – ECCV 2016. ECCV 2016, pp:391-407
[7]
J. Kim, J. K. Lee and K. M. Lee, "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 1646-1654
[8]
C. Ledig, "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 105-114
[9]
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
[10]
He K, Zhang X, Ren S, Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778
[11]
W. Shi, "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 1874-1883
Recommendations
Deep Residual Attention Network for Spectral Image Super-Resolution
Computer Vision – ECCV 2018 WorkshopsAbstractSpectral imaging sensors often suffer from low spatial resolution, as there exists an essential tradeoff between the spectral and spatial resolutions that can be simultaneously achieved, especially when the temporal resolution needs to be ...
Dilated projection correction network based on autoencoder for hyperspectral image super-resolution
AbstractThis paper focuses on improving the spatial resolution of the hyperspectral image (HSI) by taking the prior information into consideration. In recent years, single HSI super-resolution methods based on deep learning have achieved good ...
Highlights- We transform the single HSI SR problem into the abundance domain.
- We deploy a ...
Spatial-Spectral Deep Residual Network for Hyperspectral Image Super-Resolution
AbstractRecently, single hyperspectral image super-resolution (SR) methods based on deep learning have been extensively studied. However, there has been limited technical development focusing on single hyperspectral image super-resolution due to the high-...
Comments
Information & Contributors
Information
Published In
December 2021
699 pages
ISBN:9781450385053
DOI:10.1145/3508546
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
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ACAI'21
ACAI'21: 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence
December 22 - 24, 2021
Sanya, China
Acceptance Rates
Overall Acceptance Rate 173 of 395 submissions, 44%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 42Total Downloads
- Downloads (Last 12 months)11
- Downloads (Last 6 weeks)0
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format