Abstract
Image super-resolution has always been a research hotspot in the field of computer vision. Recently, image super-resolution algorithms using convolutional neural networks (CNN) have achieved good performance. But the existing methods based on CNN usually has to many (20–30) convolution layers, which has a large amount of calculations. In response to this problem, this paper proposes a lightweight network model based on parallel convolution, skip connections and ResNet. Parallel convolution means that different sizes of convolution kernels are set in the same convolutional layer to extract image features of different scales. In addition, in order to reduce the loss of image details, we combine the input and output of the previous layer as the input of the next layer, which is the skip connection. We also borrowed the idea of Residual Net. The network learns the residuals between high-resolution images and low-resolution images. Therefore, the algorithm proposed in this paper not only achieves the most advanced performance, but also achieves faster calculations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tsai, R.Y.: Multiframe image restoration and registration. Adv. Comput. Vis. Image Process. 1, 317–339 (1984)
Ur, H., Gross, D.: Improved resolution from subpixel shifted pictures. CVGIP: Graph. Models Image Process. 54(2), 181–186 (1992)
Komatsu, T., et al.: Signal-processing based method for acquiring very high resolution images with multiple cameras and its theoretical analysis. IEE Proc. I (Commun. Speech Vis.) 140(1), 19–25 (1993)
Komatsu, T., et al.: Very high resolution imaging scheme with multiple different-aperture cameras. Sign. Proces. Image Commun. 5(5-6), 511–526 (1993)
Tappen, M.F., Russell, B.C., Freeman, W.T.: Exploiting the sparse derivative prior for super-resolution and image demosaicing. In: IEEE Workshop on Statistical and Computational Theories of Vision (2003)
Kim, K.I., Kwon, Y.: Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 6, 1127–1133 (2010)
Dai, S., et al.: Soft edge smoothness prior for alpha channel super resolution. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2007. IEEE (2007)
Yang, X., et al.: An improved iterative back projection algorithm based on ringing artifacts suppression. Neurocomputing 162, 171–179 (2015)
Dong, C., et al.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Tong, T., et al.: Image super-resolution using dense skip connections. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE (2017)
Mao, X.-J., Shen, C., Yang, Y.-B.: Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv preprint arXiv:1606.08921 (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Yang, J., et al.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
Arbelaez, P., et al.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)
Bevilacqua, M., et al.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding, p. 135-1 (2012)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., et al. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27413-8_47
Kinga, D., Ba Adam, J.: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR), vol. 5 (2015)
Acknowledgements
This work was supported by the Natural Science Foundation of China (No. 61502283). Natural Science Foundation of China (No. 61472231). Natural Science Foundation of China (No. 61640201).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Q., Qi, F. (2019). Single Image Super-Resolution by Parallel CNN with Skip Connections and ResNet. In: Tang, Y., Zu, Q., Rodríguez García, J. (eds) Human Centered Computing. HCC 2018. Lecture Notes in Computer Science(), vol 11354. Springer, Cham. https://doi.org/10.1007/978-3-030-15127-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-15127-0_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-15126-3
Online ISBN: 978-3-030-15127-0
eBook Packages: Computer ScienceComputer Science (R0)