[1]WANG Fanchao,DING Shifei.Image super-resolution reconstruction based on widely activated deep residual networks[J].CAAI Transactions on Intelligent Systems,2022,17(2):440-446.[doi:10.11992/tis.202106023]
Copy

Image super-resolution reconstruction based on widely activated deep residual networks

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 17 Number of periods: 2022 2 Page number: 440-446 Column: 吴文俊人工智能科学技术奖论坛 Public date: 2022-03-05
Title:
Image super-resolution reconstruction based on widely activated deep residual networks
Author(s):
WANG Fanchao1;  DING Shifei1; 2
1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;
2. Mine Digitization Engineering Research Center of Ministry of Education of the People’s Republic of China, Xuzhou 221116, China
Keywords:
deep learning; super-resolution; extensive activation; perceptual loss; feature reconstruction; peak signal-to-noise ratio; structural similarity; visual experience
CLC:
TP391.41
DOI:
10.11992/tis.202106023
Abstract:
To obtain good image evaluation indexes, the mean squared error loss is used as an objective optimization function in image super-resolution technologies combined with the deep learning method. However, most constructed images cannot meet the visual experience requirement due to the serious loss of high-frequency signals and fuzzy texture edges. In response to the above problems, in this paper, we propose a super-resolution model for a widely activated deep residual network combining perceptual loss. A new loss function is formed by introducing perceptual and adversarial losses and is optimized by adjusting the weight of different losses. The loss function is optimized to improve the feature reconstruction ability of low-resolution images and highly restore the high-frequency information missing from the images. Two internationally recognized evaluation indicators, namely, peak signal-to-noise ratio and structural similarity, are selected as objective evaluation criteria. A comparative analysis is performed on different datasets, and the images produced are subjected to direct and subjective observations. The results show that the performance of the proposed method is improved in different aspects in comparison with the compared models. Hence, after the introduction of perceptual loss, the model can effectively reconstruct the texture details of low-resolution images and offer an outstanding visual experience.
References:
[1] 雷鹏程, 刘丛, 唐坚刚, 等. 分层特征融合注意力网络图像超分辨率重建[J]. 中国图象图形学报, 2020, 25(9): 1773–1786
LEI Pengcheng, LIU Cong, TANG Jiangang, et al. Hierarchical feature fusion attention network for image super-resolution reconstruction[J]. Journal of image and graphics, 2020, 25(9): 1773–1786
[2] HUANG Zhengzhong, CAO Liangcai. Bicubic interpolation and extrapolation iteration method for high resolution digital holographic reconstruction[J]. Optics and lasers in engineering, 2020, 130: 106090.
[3] HAO Sai, DONG Xianghuai. Interpolation-based plane stress anisotropic yield models[J]. International journal of mechanical sciences, 2020, 178: 105612.
[4] 贺璟, 郝晓丽, 吕进来. 梯度插值与可变阈值改进的POCS算法[J]. 中国科技论文, 2017, 12(14): 1655–1658,1684
HE Jing, HAO Xiaoli, Lü Jinlai. POCS algorithm based on gradient interpolation and variable threshold[J]. China sciencepaper, 2017, 12(14): 1655–1658,1684
[5] 白蔚, 杨撒博雅, 刘家瑛, 等. 基于显著性稀疏表示的图像超分辨率算法[J]. 中国科技论文, 2014, 9(1): 103–107
BAI Wei, YANG Saboya, LIU Jiaying, et al. Image super resolution based on salient sparse coding[J]. China sciencepaper, 2014, 9(1): 103–107
[6] DONG Chao, LOY C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland, 2014: 184?199.
[7] KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 1646?1654.
[8] LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, USA, 2017: 136?144.
[9] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France, 2015: 448-456.
[10] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10)[2021-01-01].https://arxiv.org/abs/1409.1556.
[11] SHI Wenzhe, CABALLERO J, HUSZáR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 1874-1883.
[12] LEDIG C, THEIS L, HUSZáR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 4681-4690.
[13] ZHANG Yulun, TIAN Yapeng, KONG Yu, et al. Residual dense network for image super-resolution[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 2472-2481.
[14] YU Jiahui, FAN Yuchen, YANG Jianchao, et al. Wide activation for efficient and accurate image super-resolution[EB/OL]. (2018-12-21)[2021-01-01]. https://arxiv.org/abs/1808.08718v1.
[15] WANG Xintao, YU Ke, WU Shixiang, et al. ESRGAN: enhanced super-resolution generative adversarial networks[C]//Proceedings of the European Conference on Computer Vision. Munich, Germany, 2018: 63?79.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems