双重判别的SAR图像超分辨率重建
SAR Image Super-Resolution Reconstruction Based on Dual Discrimination
DOI: 10.12677/CSA.2021.116167, PDF,   
作者: 肖光义, 董张玉：合肥工业大学计算机与信息学院，安徽 合肥；杨学志：合肥工业大学软件学院，安徽 合肥
关键词: 合成孔径雷达；超分辨率；生成对抗网络；双重判别；Synthetic Aperture Radar； Super-Resolution； Generative Adversarial Network； Dual Discrimination
摘要: 基于生成对抗网络的SAR图像超分辨率重建算法可以产生非常好的视觉效果。但是，现有的生成对抗网络在图像超分辨率重建的过程中仅判别生成的高分辨率图像，而忽略了低分辨率图像的作用。这不能保证生成的高分辨率图像可以被准确地降采样到最初的低分辨率图像。为了有效利用高分辨率图像和低分辨率图像，提出了双重判别的SAR图像超分辨率重建算法。双重判别在对高分辨率图像进行判别的基础上增加对低分辨率图像的判别，这使生成的高分辨率图像可以被准确地降采样到原始的低分辨率图像。而且，生成器网络在残差密集网络的基础上，融合了不同层次的变换特征，提高了参数利用率。提出的双重判别算法已成功应用于SAR图像，并且在视觉效果和客观评估指标方面都优于最新的深度学习算法。
Abstract: Synthetic Aperture Radar (SAR) image super-resolution reconstruction algorithms based on Generative Adversarial Networks (GANs) can produce very good visual effects. However, the existing super-resolution reconstruction algorithms based on GANs discriminate only the generated high-resolution images but ignore the role of low-resolution images. It fails to guarantee that the generated high-resolution image can be accurately downsampled to the original low-resolution image. In order to effectively utilize high-resolution images and low-resolution images, a dual discriminative GAN is proposed for SAR image super-resolution reconstruction. Dual discrimination increases the discrimination of the low-resolution images based on the discrimination of the high-resolution images, which enables the generated high-resolution images to be accurately downsampled to the original low-resolution images. Moreover, the generator network integrates different levels of transformation feature based on the residual dense network, which improves the parameter utilization. The proposed dual discrimination algorithm has been successfully applied to SAR images, and is superior to the latest deep learning algorithms in terms of visual effects and objective evaluation indicators.
文章引用：肖光义, 董张玉, 杨学志. 双重判别的SAR图像超分辨率重建[J]. 计算机科学与应用, 2021, 11(6): 1617-1626. https://doi.org/10.12677/CSA.2021.116167

参考文献

[1] Ledig, C., Theis, L., Huszár, F., Caballero, J., Aitken, A., Tejani, A., Totz, J., Wang, Z. and Shi, W. (2017) Pho-to-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. 2017 IEEE Conference on Com-puter Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 105-114. [Google Scholar] [CrossRef] 
[2] Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y.-H., Dong, C., Loy, C.C., Qiao, Y. and Tang, X. (2018) ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. European Conference on Computer Vision Workshops, Munich, 8-14 September 2018, 63-79. [Google Scholar] [CrossRef] 
[3] Pathak, H., Li, X., Minaee, S. and Cowan, B. (2018) Efficient Super Resolution for Large-Scale Images Using Attentional GAN. 2018 IEEE International Conference on Big Data (Big Data), Seattle, 10-13 December 2018, 1777-1786. [Google Scholar] [CrossRef] 
[4] Lim, B., Son, S., Kim, H., Nah, S. and Lee, K.M. (2017) En-hanced Deep Residual Networks for Single Image Super-Resolution. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, 21-26 July 2017, 1132-1140. [Google Scholar] [CrossRef] 
[5] Freeman, W., Jones, T. and Pasztor, E. (2002) Example-Based Super-Resolution. IEEE Computer Graphics and Applications, 22, 56-65. [Google Scholar] [CrossRef] 
[6] Huang, J.-B., Singh, A. and Ahuja, N. (2015) Single Image Su-per-Resolution from Transformed Self-Exemplars. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 5197-5206. [Google Scholar] [CrossRef] 
[7] Yang, J., Wright, J., Huang, T. and Ma, Y. (2010) Image Su-per-Resolution via Sparse Representation. IEEE Transactions on Image Processing, 19, 2861-2873. [Google Scholar] [CrossRef] 
[8] Gu, S., Zuo, W., Xie, Q., Meng, D., Feng, X. and Zhang, L. (2015) Convolutional Sparse Coding for Image Super-Resolution. 2015 IEEE International Conference on Computer Vision, Santiago, 7-13 December 2015, 1823-1831. [Google Scholar] [CrossRef] 
[9] Dong, C., Loy, C.C., He, K. and Tang, X. (2016) Image Su-per-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 295-307. [Google Scholar] [CrossRef] 
[10] Dong, C., Loy, C.C. and Tang, X. (2016) Accelerating the Super-Resolution Convolutional Neural Network. European Conference on Computer Vision, Amsterdam, 8-16 October 2016, 391-407. [Google Scholar] [CrossRef] 
[11] Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A., Bishop, R., Rueckert, D. and Wang, Z. (2016) 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, Las Vegas, 27-30 June 2016, 1874-1883. [Google Scholar] [CrossRef] 
[12] Tong, T., Li, G., Liu, X. and Gao, Q. (2017) Image Su-per-Resolution Using Dense Skip Connections. 2017 IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 4809-4817. [Google Scholar] [CrossRef] 
[13] Zhang, Y., Tian, Y., Kong, Y., Zhong, B. and Fu, Y. (2018) Residual Dense Network for Image Super-Resolution. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2472-2481. [Google Scholar] [CrossRef] 
[14] Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X. and Tang, X. (2017) Residual Attention Network for Image Classifica-tion. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 6450-6458. [Google Scholar] [CrossRef] 
[15] Zhang, Y., Li, K.P., Li, K., Wang, L., Zhong, B. and Fu, Y. (2018) Image Super-Resolution Using Very Deep Residual Channel Attention Networks. European Conference on Computer Vision 2018, Munich, 8-14 September, 294-310. [Google Scholar] [CrossRef] 
[16] Muqeet, A., Tauhid Bin Iqbal, Md. and Bae, S.-H. (2019) HRAN: Hybrid Residual Attention Network for Single Image Super-Resolution. IEEE Access, 7, 137020-137029. [Google Scholar] [CrossRef] 
[17] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C. and Bengio, Y. (2014) Generative Adversarial Nets. Neural Information Processing Systems 2014, Bangkok, 23-27 November 2014, 2672-2680.
[18] Karras, T., Laine, S. and Aila, T. (2019) A Style-Based Generator Architecture for Generative Adversarial Networks. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 4396-4405. [Google Scholar] [CrossRef] 
[19] Phillip, I., Zhu, J.-Y., Zhou, T. and Efros, A.A. (2017) Im-age-to-Image Translation with Conditional Adversarial Networks. 2017 IEEE Conference on Computer Vision and Pat-tern Recognition, Honolulu, July 2017, 5967-5976.
[20] Zhu, J.-Y., Park, T., Isola, P. and Efros, A.A. (2017) Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. 2017 IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 2242-2251. [Google Scholar] [CrossRef] 
[21] Alexia, J.-M. (2019)The Relativistic Discriminator: A Key Element Missing from Standard GAN. ArXiv abs/1807.00734.
[22] Sajjadi, M.S.M., Schölkopf, B. and Hirsch, M. (2017) EnhanceNet: Single Image Su-per-Resolution through Automated Texture Synthesis. 2017 IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 4501-4510. [Google Scholar] [CrossRef] 
[23] Park, S., Son, H., Cho, S., Hong, K.-S. and Lee, S. (2018) SRFeat: Single Image Super-Resolution with Feature Discrimination. European Conference on Computer Vision 2018, Munich, 8-14 September, 455-471. [Google Scholar] [CrossRef]