Abstract
Recent studies have shown that the use of deep convolutional neural networks (CNNs) can improve the performance of single image super-resolution reconstruction (SISR) methods. However, the existing CNN-based SISR model ignores the multi-scale features and shallow and deep features of the image, resulting in relatively low image reconstruction performance. To address these issues, this paper proposes a new multi-scale fractal residual network (MSFRN) for image super-resolution. On the basis of residual learning, a multi-scale fractal residual block (MSFRB) is designed. This block uses convolution kernels of different sizes to extract image multi-scale features and uses multiple paths to extract and fuse image features of different depths. Then, the shallow features extracted at the shallow feature extraction stage and the local features output by all MSFRBs are used to perform global hierarchical feature fusion. Finally, through sub-pixel convolution, the fused global features are used to reconstruct high-resolution images from low-resolution images. The experimental results on the five standard benchmark datasets show that MSFRN improved subjective visual effects and objective image quality evaluation indicators, and is superior to other state-of-the-art SISR methods.
Similar content being viewed by others
References
Zhang H, Yang Z, Zhang L, Shen H (2013) Super-resolution reconstruction for multi-angle remote sensing images considering resolution differences. Remote Sens 6(1):637–657
Zou WWW, Yuen PC (2012) Very low resolution face recognition problem. IEEE Trans Image Process 21(1):327–340
Shi W, Caballero J, Ledig C, Zhuang X, Bai W, Bhatia K, De Marvao AMSM, Dawes T, O’Regan D, Rueckert D (2013) Cardiac image super-resolution with global correspondence using multi-atlas PatchMatch. In: 16th International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 9-16
Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10(10):1521–1527
Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15(8):2226–2238
Tai Y-W, Liu S, Brown MS, Lin S (2010) Super resolution using edge prior and single image detail synthesis. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2400–2407
Zhang K, Gao X, Member S, IEEE, Tao D (2012) Single image super-resolution with non-local means and steering kernel regression. IEEE Trans Image Process 21(11):4544–4556
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1646-1654
Kim J, Lee JK, Lee KM (2016) deeply-recursive convolutional network for image super-resolution. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1637-1645
Lai W-S, Huang J-B, Ahuja N, Yang M-H (2017) Deep laplacian pyramid networks for fast and accurate super-resolution. In: proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 5835-5843
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: Proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2790-2798
Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 105-114
N. Ahn, B. Kang, K.-A. Sohn (2018) Fast, accurate, and lightweight super-resolution with cascading residual network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 252-268
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1132-1140
Cao F, Liu H (2019) Single image super-resolution via multi-scale residual channel attention network. Neurocomputing 358:424–436
Shi W, Caballero J, Huszar F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1874-1883
Jiang K, Wang Z, Yi P, Jiang J (2020) Hierarchical dense recursive network for image super-resolution. Pattern Recogn 107:107475
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261-2269
Larsson G, Maire M, Shakhnarovich G (2017) FractalNet: ultra-deep neural networks without residuals. In: 5th international conference on Learning Representations
Zhou Y, Dong J, Yang Y (2019) Deep fractal residual network for fast and accurate single image super resolution. Neurocomputing
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 770–778
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: 28th Annual Conference on Neural Information Processing Systems 2014, pp. 2672–2680
Cao F, Chen B (2019) New architecture of deep recursive convolution networks for super-resolution. Knowl-Based Syst 178:98–110
Soh JW, Cho NI (2020) Lightweight single image super-resolution with multi-scale spatial attention networks. IEEE Access 8:35383–35391
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-ResNet and the impact of residual connections on learning. In: 31st AAAI Conference on Artificial Intelligence, pp. 4278-4284
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2472–2481
Qin J, Huang Y, Wen W (2020) Multi-scale feature fusion residual network for single image super-resolution. Neurocomputing 379:334–342
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–9
Yu W, Yang K, Yao H, Sun X, Xu P (2017) Exploiting the complementary strengths of multi-layer CNN features for image. Neurocomputing 237:235–241
Zhao H, Gallo O, Frosio I, Kautz J (2017) Loss functions for image restoration with neural networks. IEEE Transactions on Computational Imaging 3(1):47–57
Timofte R, Agustsson E, Gool LV, Yang M-H, Zhang L, Lim B et al (2017) NTIRE 2017 challenge on single image super-resolution: methods and results. In: 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1110-1121
Bevilacqua M, Roumy A, Guillemot C, Morel M-LA (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding, In: Proceedings of British Machine Vision Conference, pp. 1-10
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: 7th International Conference on Curves and Surfaces, pp. 711-730
Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the IEEE International Conference on Computer Vision,pp. 416–423
Huang J-B, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 5197–5206
Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K (2017) Sketch-based manga retrieval using manga109 dataset. Multimed Tools Appl 76(20):21811–21838
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: ICLR 2015 - conference track proceedings
A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, A. Lerer (2017) Automatic differentiation in pytorch, Advances in Neural Information Processing Systems Autodiff Workshop
Keys RG (1981) Cubic convolution interpolation for digital image processing. IEEE Transactions on Acoustics, Speech, and Signal Processing ASSP 29(6):1153–1160
Timofte R, de Smet V, van Gool L (2015) A+: adjusted anchored neighborhood regression for fast super-resolution. In: 12th Asian Conference on Computer Vision, pp. 111-126
Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. In: 14th European Conference on Computer Vision(ECCV), pp. 391-407
Li J, Fang F, Mei K, Zhang G (2018) Multi-scale residual network for image super-resolution. In: 15th European Conference on Computer Vision, pp. 527-542
Acknowledgments
This work was supported by the Science and Technology Support of Tianjin Key Research and the Development Plan Project (Grant no.18YFZCGX00930). The authors also acknowledge the anonymous reviewers for their helpful comments on the manuscript.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Feng, X., Li, X. & Li, J. Multi-scale fractal residual network for image super-resolution. Appl Intell 51, 1845–1856 (2021). https://doi.org/10.1007/s10489-020-01909-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01909-8