Abstract
The in-depth development of generative adversarial networks in the field of specific application tasks, the single image super-resolution problem has been widely studied. We proposed a novel reconstruction model using generative adversarial network for single image super-resolution reconstruction task. Our model directly learns an end-to-end mapping between the low and high-resolution images. The mapping is represented as a generative adversarial network that takes the low-resolution images as the input and outputs the high-resolution one. We further confirmed that the spectral normalization and attention method is exceedingly effective for the training of stably generating adversarial networks. We use a more lightweight external attention method in the network to accelerate the speed of global structure reconstruction. It is different from the previous image super-resolution task. Our model implements multi-scale joint training and optimizes all layers. We explore different networks structures and parameter settings to achieve trade-offs between performance and speed. Quantitative indexes and qualitative results show that our proposed method achieves comparable performance with the state-of-the-art supervised models.
Similar content being viewed by others
References
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. IEEE Conf Comput Vis Pattern Recogn Workshops (CVPRW) 2017:1132–1140. https://doi.org/10.1109/CVPRW.2017.151
Nan F, Zeng Q, Xing Y, Qian Y (2020) Single image super-resolution reconstruction based on the ResNeXt network. Multimed Tools Appl 79:34459–34470. https://doi.org/10.1007/s11042-020-09053-8
Chu J, Li X, Zhang J, Lu W (2020) Super-resolution using multi-channel merged convolutional network. Neurocomputing 394:136–145. https://doi.org/10.1016/j.neucom.2019.04.089
Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. IEEE Conf Comput Vis Pattern Recogn (CVPR) 2017:5967–5976. https://doi.org/10.1109/CVPR.2017.632
Wu X, Li Y, Hao Z, Wu C, Wang X, Liu Y (2019) Image style transformation based on structure GAN. Chin Autom Congr (CAC) 2019:2002–2007. https://doi.org/10.1109/CAC48633.2019.8996315
Meng Y, Kong D, Zhu Z, Zhao Y (2019) From night to day: GANs based low quality image enhancement. Neural Process Lett 50:799–814. https://doi.org/10.1007/s11063-018-09968-2
Tian C, Xu Y, Zuo W (2020) Image denoising using deep CNN with batch renormalization. Neural Netw 121:461–473. https://doi.org/10.1016/j.neunet.2019.08.022
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307. https://doi.org/10.1109/TPAMI.2015.2439281
Lin G, Wu Q, Qiu L, Huang X (2018) Image super-resolution using a dilated convolutional neural network. Neurocomputing 275:1219–1230. https://doi.org/10.1016/j.neucom.2017.09.062
Lai W-S, Huang J-B, Ahuja N, Yang M-H (2017) Deep Laplacian pyramid networks for fast and accurate super-resolution. IEEE Conf Comput Vis Pattern Recogn (CVPR) 2017:5835–5843. https://doi.org/10.1109/CVPR.2017.618
Wang Y, Perazzi F, McWilliams B, Sorkine-Hornung A, Sorkine-Hornung O, Schroers C (2018) A fully progressive approach to single-image super-resolution. IEEE/CVF Conf Comput Vis Pattern Recogn Workshops (CVPRW) 2018:977–97709. https://doi.org/10.1109/CVPRW.2018.00131
Shaham TR, Dekel T, Michaeli T (2019) SinGAN: learning a generative model from a single natural image. IEEE/CVF Int Conf Comput Vis (ICCV) 2019:4569–4579. https://doi.org/10.1109/ICCV.2019.00467
Li Y, Huang H, Zhang L, Wang G, Zhang H, Zhou W (2020) Super-resolution and self-attention with generative adversarial network for improving malignancy characterization of hepatocellular carcinoma. IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020, pp 1556–1560
Seddik MEA, Tamaazousti M, Lin J (2020) Generative collaborative networks for single image super-resolution. Neurocomputing 398:293–303. https://doi.org/10.1016/j.neucom.2019.02.068
Zhao M, Liu X, Liu H, Wong KKL (2020) Super-resolution of cardiac magnetic resonance images using Laplacian Pyramid based on Generative Adversarial Networks. Comput Med Imaging Graph 80:101698. https://doi.org/10.1016/j.compmedimag.2020.101698
Yu L, Long X, Tong C (2018) Single image super-resolution based on improved WGAN. Atlantis Press, pp 101–104
Zong L, Chen L (2019) Single image super-resolution based on self-attention. IEEE Int Conf Unmanned Syst Artif Intell (ICUSAI) 2019:56–60. https://doi.org/10.1109/ICUSAI47366.2019.9124791
Wang M, Chen Z, Wu QMJ, Jian M (2020) Improved face super-resolution generative adversarial networks. Mach Vis Appl 31:22. https://doi.org/10.1007/s00138-020-01073-6
Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X et al (2019) StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans Pattern Anal Mach Intell 41:1947–1962. https://doi.org/10.1109/TPAMI.2018.2856256
Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X et al (2017) StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. IEEE Int Conf Comput Vis (ICCV) 2017:5908–5916. https://doi.org/10.1109/ICCV.2017.629
Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C et al (2019) ESRGAN: enhanced super-resolution generative adversarial networks. In: Leal-Taixé L, Roth S (eds) Computer Vision—ECCV 2018 Workshops. Springer, Cham, pp 63–79
Hinz T, Fisher M, Wang O, et al. (2021) Improved techniques for training single-image GANs[A]. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)[C]. pp. 1299–1308
Du J, Cheng K, Yu Y, Wang D, Zhou H (2020) Panchromatic image super-resolution via self attention-augmented WGAN 2020
Guo M-H, Liu Z-N, Mu T-J, Hu S-M (2021) Beyond self-attention: external attention using two linear layers for visual tasks. arXiv 2021. arXiv preprint arXiv:2105.02358
Xiaopeng C, Jiangzhong C, Yuqin L, Qingyun D (2020) Improved training of spectral normalization generative adversarial networks. 2020 2nd World Symposium on Artificial Intelligence (WSAI), pp 24–28
Lan Z, Lin M, Li X, Hauptmann AG, Raj B (2015) Beyond Gaussian pyramid: multi-skip feature stacking for action recognition. IEEE Conf Comput Vis Pattern Recogn (CVPR) 2015:204–212. https://doi.org/10.1109/CVPR.2015.7298616
Burt P, Adelson E (1983) The Laplacian pyramid as a compact image code. IEEE Trans Commun 31:532–540. https://doi.org/10.1109/TCOM.1983.1095851
Paris S, Hasinoff SW, Kautz J (2011) Local Laplacian filters: edge-aware image processing with a Laplacian pyramid. ACM Trans Graph 30:1–12. https://doi.org/10.1145/2010324.1964963
Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. IEEE/CVF Conf Comput Vis Pattern Recogn 2018:7794–7803. https://doi.org/10.1109/CVPR.2018.00813
Garbin C, Zhu X, Marques O (2020) Dropout vs. batch normalization: an empirical study of their impact to deep learning. Multimed Tools Appl 79:12777–12815. https://doi.org/10.1007/s11042-019-08453-9
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of Wasserstein GANs. Adv Neural Inf Process Syst (NeurIPS) 2017:5767–5777
Chen X, Zhao H, Yang D, Li Y, Kang Q, Lu H (2021) SA-SinGAN: self-attention for single-image generation adversarial networks. Mach Vis Appl 32:104. https://doi.org/10.1007/s00138-021-01228-z
Peng D, Yang W, Liu C, Lü S (2021) SAM-GAN: self-attention supporting multi-stage generative adversarial networks for text-to-image synthesis. Neural Netw 138:57–67. https://doi.org/10.1016/j.neunet.2021.01.023
Karras T, Aila T, Laine S, Lehtinen J (2018) Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196
Obukhov A, Krasnyanskiy M (2020) Quality assessment method for GAN based on modified metrics inception score and Fréchet Inception distance. In: Silhavy R, Silhavy P, Prokopova Z (eds) Software engineering perspectives in intelligent systems. Springer, Cham, pp 102–114
Erfurt J, Helmrich CR, Bosse S, Schwarz H, Marpe D, Wiegand T (2019) A study of the perceptually weighted peak signal-to-noise ratio (WPSNR) for image compression. IEEE Int Conf Image Process (ICIP) 2019:2339–2343. https://doi.org/10.1109/ICIP.2019.8803307
Ćalasan M, Abdel Aleem SHE, Zobaa AF (2020) On the root mean square error (RMSE) calculation for parameter estimation of photovoltaic models: a novel exact analytical solution based on Lambert W function. Energy Convers Manag 210:112716. https://doi.org/10.1016/j.enconman.2020.112716
Zhang L, Zhang L, Bovik AC (2015) A feature-enriched completely blind image quality evaluator. IEEE Trans Image Process 24:2579–2591. https://doi.org/10.1109/TIP.2015.2426416
Lempitsky V, Vedaldi A, Ulyanov D (2018) Deep image prior. In: IEEE Computer Society
Shocher A, Cohen N, Irani M (2018) Zero-shot super-resolution using deep internal learning. In: IEEE Computer Society
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, X., Zhao, H. A Novel Fast Reconstruction Method for Single Image Super Resolution Task. Neural Process Lett 55, 9995–10010 (2023). https://doi.org/10.1007/s11063-023-11235-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-023-11235-y