Abstract
Single image super-resolution (SISR) is an important research field in computer vision, the purpose of which is to recover clear, high-resolution (HR) images from low-resolution (LR) images. With the rapid developments in deep learning theory and technology, deep learning has been introduced into the field of image super-resolution (SR), and has achieved results far beyond traditional methods in many domains. This paper summarizes current image SR algorithms based on deep learning. Firstly, the mainstream frameworks, loss functions, and datasets used for SISR are introduced in detail. Then, the SISR algorithm based on deep learning is explored using three models: a convolutional neural network (CNN), a generative adversarial network (GAN), and a transformer. Next, the evaluation indices used for SR are introduced, and the reconstruction results from various algorithms based on deep learning are compared. Finally, future trends in research on image SR algorithms based on deep learning are summarized.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available in the following repositories: Set5(https://www.kaggle.com/msahebi/super-resolution), Set14(https://www.kaggle.com/msahebi/super-resolution), BSD100(https://www.kaggle.com/msahebi/super-resolution), Urban100(https://drive.google.com/drive/folders/1pRmhEmmY-tPF7uH8DuVthfHoApZWJ1QU?usp=sharing), Manga109(http://www.manga109.org/en/index.html), DIV2K(https://data.vision.ee.ethz.ch/cvl/DIV2K/), Flickr2K(https://drive.google.com/drive/folders/1B-uaxvV9qeuQ-t7MFiN1oEdA6dKnj2vW), RealSR(https://drive.google.com/open?id=17ZMjo-zwFouxnm_aFM6CUHBwgRrLZqIM), DPED(https://drive.google.com/file/d/0BwOLOmqkYj-jeUJwQjRNUFkzOTA/view), OutdoorScene(https://drive.google.com/drive/u/1/folders/ 1iZfzAxAwOpeutz27HC56_y5RNqnsPPKr), PIRM(https://drive.google.com/drive/folders/ 17FmdXu5t8wlKwt8extb_nQAdjxUOrb1O?usp = sharing), T91(https://drive.google.com/drive/folders/1pRmhEmmY-tPF7uH8DuVthfHoApZWJ1QU?usp=sharing),ImageNet(https://image-net.org/challenges/LSVRC/), City100(https://github.com/ngchc/CameraSR), MSCOCO(https://cocodataset.org/#download), PIPAL(https://github.com/HaomingCai/PIPAL-dataset).
References
Huang TJCV, Processing I (1984) Multi-frame image restoration and registration. Multiframe Image Restor Registration 1:317–339
Greenspan HJTCJ (2009) Super-resolution in medical imaging. Comput J 52:43–63
Isaac JS, Kulkarni R (2015) Super resolution techniques for medical image processing. 2015 International Conference on Technologies for Sustainable Development (ICTSD). IEEE, pp 1–6
Huang Y, Shao L, Frangi AF (2017) Simultaneous super-resolution and cross-modality synthesis of 3D medical images using weakly-supervised joint convolutional sparse coding. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 5787–5796
Thornton MW, Atkinson PM, Holland DJIJORS (2006) Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping. Int J Remote Sens 27:473–491
Barzegar S, Sharifi A, Manthouri MJMT et al (2020) Super-resolution using lightweight detailnet network. Multimed Tools Appl 79:1119–1136
Yang W, Zhou F, Zhu R et al (2019) Deep learning for image super-resolution. Neurocomputing 398:291–292
Timofte R, Rothe R, Van Gool L (2016) Seven ways to improve example-based single image super resolution. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1865–1873
Zeyde R, Elad M, Protter M (2012) On single image scale-up using sparse-representations. Curves and Surfaces: 7th International Conference. Springer, pp 711–730
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1664–1673
Lai W-S, Huang J-B, Ahuja N et al (2017) Deep laplacian pyramid networks for fast and accurate super-resolution. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 5835–5843
Ledig C, Theis L, Huszár F et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 105–114
Bevilacqua M, Roumy A, Guillemot C et al (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. 23rd British Machine Vision Conference, pp 1–10.
Huang J-B, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 5197–5206
Martin D, Fowlkes C, Tal D et al (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001. IEEE, pp 416–423
Fujimoto A, Ogawa T, Yamamoto K et al (2016) Manga109 dataset and creation of metadata. 1st international workshop on comics analysis, processing and understanding (MANPU), pp 1–5
Agustsson E, Timofte R (2017) Ntire 2017 challenge on single image super-resolution: Dataset and study. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1122–1131
Xia B, Hang Y, Tian Y et al (2022) Efficient non-local contrastive attention for image super-resolution. 36th AAAI Conference on Artificial Intelligence 36(3): 2759–2767
Lee J, Jin KH (2022) Local texture estimator for implicit representation function. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1929–1938
Ma C, Zhang J, Zhou J et al (2022) Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution. 17th European Conference on Computer Vision (ECCV). Springer, 13677: 305–321
Timofte R, Agustsson E, Van Gool L et al (2017) Ntire 2017 challenge on single image super-resolution: Methods and results. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1110–1121
Zhou L, Cai H, Gu J et al (2022) Efficient image super-resolution using vast-receptive-field attention. European Conference on Computer Vision (ECCV). Springer, pp 256–272
Ji X, Cao Y, Tai Y et al (2020) Real-world super-resolution via kernel estimation and noise injection. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). IEEE, pp 1914–1923
Liang J, Zeng H, Zhang L (2022) Efficient and degradation-adaptive network for real-world image super-resolution. 17th European Conference on Computer Vision (ECCV). Springer, 13867: 574–591
Cai J, Zeng H, Yong H et al (2019) Toward real-world single image super-resolution: A new benchmark and a new model. IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 3086–3095
Deng J, Dong W, Socher R et al (2009) Imagenet: A large-scale hierarchical image database. IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE, pp 248–255
Ignatov A, Kobyshev N, Timofte R et al (2017) Dslr-quality photos on mobile devices with deep convolutional networks. 16th IEEE International Conference on Computer Vision (ICCV). IEEE, pp 3297–3305
Wang X, Yu K, Dong C et al (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 606–615
Blau Y, Mechrez R, Timofte R et al (2018) The 2018 PIRM challenge on perceptual image super-resolution. 15th European Conference on Computer Vision (ECCV), vol 11133. Springer, pp 334–355
Yang J, Wright J, Huang TS et al (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19:2861–2873
Yoo J, Kim T, Lee S et al (2022) Enrich CNN-transformer feature aggregation networks for super-resolution. 23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp 4945–4954
Lin T-Y, Maire M, Belongie S et al (2014) Microsoft coco: common objects in context. 13th European Conference on Computer Vision (ECCV), vol 8693. Springer, pp 740–755
Jinjin G, Haoming C, Haoyu C et al (2020) Pipal: a large-scale image quality assessment dataset for perceptual image restoration. European Conference on Computer Vision (ECCV). Springer, pp 633–651
Chen C, Xiong Z, Tian X et al (2019) Camera lens super-resolution. 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1652–1660
Dong C, Loy CC, He K et al (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307
Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. 14th European Conference on Computer Vision (ECCV), vol 9906. Springer, pp 391–407
Shi W, Caballero J, Huszár F et al (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 (CVPR). IEEE, pp 1874–1883
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 770–778
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1646–1654
Simonyan K, Zisserman AJaPA (2015) Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations (ICLR), pp 1–14
Mao X-J, Shen C, Yang Y-BJaPA (2016) Image restoration using convolutional auto-encoders with symmetric skip connections. Neural Information Processing Systems (NIPS) 29
Lim B, Son S, Kim H et al (2017) Enhanced deep residual networks for single image super-resolution. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1132–1140
Nah S, Hyun Kim T, Mu Lee K (2017) Deep multi-scale convolutional neural network for dynamic scene deblurring. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 257–265
Szegedy C, Ioffe S, Vanhoucke V et al (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. 31st AAAI Conference on Artificial Intelligence, pp 4278–4284
Kim J, Lee JK, Lee KM (2016) Deeply-recursive convolutional network for image super-resolution. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1637–1645
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 2790–2798
Han W, Chang S, Liu D et al (2018) Image super-resolution via dual-state recurrent networks. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1654–1663
Gilbert CD, Sigman MJN (2007) Brain states: top-down influences in sensory processing. Neuron 54:677–696
Hupé J, James A, Payne B et al (1998) Cortical feedback improves discrimination between figure and background by V1, V2 and V3 neurons. Nature 394:784–787
Li Z, Yang J, Liu Z et al (2019) Feedback network for image super-resolution. 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 3867–3871
Huang G, Liu Z, Van Der Maaten L et al (2017) Densely connected convolutional networks. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 2261–2269
Tong T, Li G, Liu X et al (2017) Image super-resolution using dense skip connections. 16th IEEE International Conference on Computer Vision (ICCV). IEEE, pp 4809–4817
Tai Y, Yang J, Liu X et al (2017) Memnet: A persistent memory network for image restoration. 16th IEEE International Conference on Computer Vision (ICCV). IEEE, pp 4549–4557
Chaudhari S, Mithal V, Polatkan G et al (2021) An attentive survey of attention models. ACM Trans Intell Syst Technol (TIST) 12(5):1–32
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 7132–7141
Zhang Y, Li K, Li K et al (2018) Image super-resolution using very deep residual channel attention networks. 15th European Conference on Computer Vision (ECCV), vol 11211. Springer, pp 294–310
Dai T, Cai J, Zhang Y et al (2019) Second-order attention network for single image super-resolution. 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 11057–11066
Zhang Y, Wei D, Qin C et al (2021) Context reasoning attention network for image super-resolution. 18th IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 4258–4267
Zhao H, Kong X, He J et al (2020) Efficient image super-resolution using pixel attention. European Conference on Computer Vision (ECCV) Workshops. Springer, pp 56–72
Hui Z, Wang X, Gao X (2018) Fast and accurate single image super-resolution via information distillation network. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 723–731
Hui Z, Gao X, Yang Y et al (2019) Lightweight image super-resolution with information multi-distillation network. 27th ACM International Conference on Multimedia (MM), pp 2024–2032
Luo X, Xie Y, Zhang Y et al (2020) Latticenet: towards lightweight image super-resolution with lattice block. European Conference on Computer Vision (ECCV). Springer, pp 272–289
Zhang Y, Wang H, Qin C et al (2021) Learning efficient image super-resolution networks via structure-regularized pruning. International conference on learning representations 1–12
Zhang Y, Wang H, Qin C et al (2021) Aligned structured sparsity learning for efficient image super-resolution. Adv Neural Inf Process Syst 34:2695–2706
Wang H, Zhang Y, Qin C et al (2023) Global aligned structured sparsity learning for efficient Image super-resolution. IEEE Transactions on pattern analysis and machine intelligence. IEEE 45:10974–10989
Goodfellow I, Pouget-Abadie J, Mirza M et al (2020) Generative adversarial networks. IEEE Signal Process Mag 63:139–144
Wang X, Yu K, Wu S et al (2018) Esrgan: Enhanced super-resolution generative adversarial networks. 15th European Conference on Computer Vision (ECCV) Workshops, vol 11133. Springer, pp 63–79
Jolicoeur-Martineau AJaPA (2018) The relativistic discriminator: a key element missing from standard GAN. International Conference on Learning Representations (ICLR 2019)
Lee O-Y, Shin Y-H, Kim J-OJIA (2019) Multi-perspective discriminators-based generative adversarial network for image super resolution. IEEE Access 7:136496–136510
Rakotonirina NC, Rasoanaivo A (2020) ESRGAN+: Further improving enhanced super-resolution generative adversarial network. ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 3637–3641
Chen Y, Li J, Xiao H et al (2017) Dual path networks. 31st Annual Conference on Neural Information Processing Systems (NIPS) 30
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE, pp 4401–4410
Shi W, Tao F, Wen YJITOI et al (2023) Structure-aware deep networks and pixel-level generative adversarial training for single image super-resolution. IEEE Trans Instrum Meas 72:1–14
Isola P, Zhu J-Y, Zhou T et al (2017) Image-to-image translation with conditional adversarial networks. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 5967–5976
Ma C, Rao Y, Lu J et al (2021) Structure-preserving image super-resolution. IEEE Trans Pattern Anal Mach Intell 44:7898–7911
Ma C, Rao Y, Cheng Y et al (2020) Structure-preserving super resolution with gradient guidance. IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE, pp 7769–7778
Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. 31st Annual Conference on Neural Information Processing Systems (NIPS) 30
Arnab A, Dehghani M, Heigold G et al (2021) Vivit: A video vision transformer. 18th IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 6816–6826
Chen H, Wang Y, Guo T et al (2021) Pre-trained image processing transformer. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 12294–12305
Liu Z, Lin Y, Cao Y et al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. 18th IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 9992–10002
Liang J, Cao J, Sun G et al (2021) Swinir: Image restoration using swin transformer. 18th IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 1833–1844
Lu Z, Li J, Liu H et al (2022) Transformer for single image super-resolution. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). IEEE, pp 456–465
Zhang X, Zeng H, Guo S et al (2022) Efficient long-range attention network for image super-resolution. 17th European Conference on Computer Vision (ECCV), vol 13677. Springer, pp 649–667
Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Proc 13:600–612
Ma C, Yang C-Y, Yang X et al (2017) Learning a no-reference quality metric for single-image super-resolution. Comput Vis Image Underst 158:1–16
Zhang L, Zhang L, Mou X et al (2011) FSIM: A feature similarity index for image quality assessment. IEEE Trans Image Proc 20:2378–2386
Zhang R, Isola P, Efros AA et al (2018) The unreasonable effectiveness of deep features as a perceptual metric. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 586–595
Zhang Y, Tian Y, Kong Y et al (2018) Residual dense network for image super-resolution. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 2472–2481
Zareapoor M, Celebi ME, Yang JJSPIC (2019) Diverse adversarial network for image super-resolution. Signal Proc: Image Commun 74:191–200
Gao G, Wang Z, Li J et al (2022) Lightweight bimodal network for single-image super-resolution via symmetric cnn and recursive transformer. Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), pp 913–919
Acknowledgements
This work was supported by the following grants: National Natural Science Foundation of China: 62276088, 62102129, Natural Science Foundation of Hebei Province: F2021202030.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interests
All authors declared that we have no conflicts of interests to this work.
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
Yu, M., Shi, J., Xue, C. et al. A review of single image super-resolution reconstruction based on deep learning. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-17660-4
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-023-17660-4