Image super-resolution reconstruction based on self-attention GAN

被引：0
|
作者：
Wang X.-S. [1 ,2 ]
Chao J. [1 ,2 ]
Cheng Y.-H. [1 ,2 ]
机构：
[1] Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou
[2] School of Information and Control Engineering, China University of Mining and Technology, Xuzhou
来源：
Kongzhi yu Juece/Control and Decision | 2021年 / 36卷 / 06期
关键词：
Generative adversarial network; Image super-resolution reconstruction; Loss function; Self-attention mechanism;
D O I：
10.13195/j.kzyjc.2019.1290
中图分类号：
学科分类号：
摘要：
Aiming at how to recover the texture details of the reconstructed super-resolution image, an image super-resolution reconstruction based on the self-attention generative adversarial network (SRAGAN) is proposed. In the SRAGAN, a generator based on a combination of the self-attention mechanism and the residual module is used to transform low-resolution into super-resolution images, while a discriminator based on the deep convolutional network tries to distinguish the difference between the reconstructed and real super-resolution images. In terms of loss function construction, on the one hand, the Charbonnier content loss function is used to improve the accuracy of image reconstruction; on the other hand, the eigenvalues before the activation layer in the pre-trained VGG network are used to calculate the perceptual loss to achieve accurate texture detail reconstruction of super-resolution images. Experiments show that the proposed SRAGAN is superior to the current popular algorithms in peak signal-to-noise ratio and structural similarity score, reconstructing more realistic images with clear textures. Copyright ©2021 Control and Decision.
引用
收藏
页码：1324 / 1332
页数：8
相关论文
共 25 条
  • [1] Shi W Z, Caballero J, Ledig C, Et al., Cardiac image super-resolution with global correspondence using multi-atlas patchmatch, Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 9-16, (2013)
  • [2] Thornton M W, Atkinson P M, Holland D A., Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping, International Journal of Remote Sensing, 27, 3, pp. 473-491, (2006)
  • [3] Bilgazyev E, Efraty B, Shah S K, Et al., Improved face recognition using super-resolution, Proceedings of IEEE International Joint Conference on Biometrics, pp. 1-7, (2011)
  • [4] Chang H, Yeung D Y, Xiong Y M., Super-resolution through neighbor embedding, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1275-1282, (2004)
  • [5] Timofte R, De Smet Vincent, Van Gool Luc, A+: Adjusted anchored neighborhood regression for fast super-resolution, Proceedings of Asian Conference on Computer Vision, pp. 111-126, (2014)
  • [6] Wu C D, Lu Z W, Yu X S., Image super resolution reconstruction algorithm based on weighted random forest, Control and Decision, 34, 10, pp. 2243-2248, (2019)
  • [7] Lv E H, Wang X S, Cheng Y H., Deep convolution neural network learning based on deconvolution feature extraction, Control and Decision, 33, 3, pp. 447-454, (2018)
  • [8] Dong C, Loy C C, He K, Et al., Image super-resolution using deep convolutional networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 2, pp. 295-307, (2014)
  • [9] Kim J, Lee J K, Lee K M., Accurate image super-resolution using very deep convolutional networks, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, (2016)
  • [10] Kim J, Lee J K, Lee K M., Deeply-recursive convolutional network for image super-resolution, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637-1645, (2016)
123