Abstract
Recent researches have shown that deep convolutional neural networks can significantly boost the performance of single-image super-resolution (SISR). In particular, residual network and densely convolutional network can improve performance remarkably. The residual network enables feature re-usage and the dense skip connections enables new features exploration, which are both favor for feature extraction. In order to alleviate the vanishing-gradient problem in very deep convolution networks. In this paper, a bi-path network coupling is presented for SISR by combining the residual network and the dense skip connections in a very deep network. More specifically, the feature maps in the proposed network are split into two paths, one path is propagated in the form of residual connections, and another is propagated by dense skip connections. In addition, we input the feature maps obtained from the two paths into the coupling layer for feature fusion. Finally, the deconvolution layers are integrated into the network to upscale the feature map for significantly accelerating the network, that the mapping is learned from the low-resolution image to the high-resolution image directly. The proposed network was evaluated on four benchmark datasets and has achieved competing or even higher peak signal-to-noise ratio (PSNR) than most of state-of-the-art methods.
Similar content being viewed by others
References
Bevilacqua M, Roumy A, Guillemot C, AlberiMorel ML (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In BMVC
Bevilacqua M, Roumy A, Guillemot C, Morel M-LA (2014) Single-image superresolution via linear mapping of interpolated self-examples. IEEE Trans Image Process 23(12):5334–5347
Blu T, Thevenaz P, Unser M (2004) Linear interpolation revitalized. IEEE Trans Image Process 13(6):710–719
Chen Y, Li J, Xiao H et al. (2017) Dual path networks[C]//Advances in Neural Information Processing Systems. 4470-4478
Dai S, Han M, Xu W, Wu Y, Gong Y, Katsaggelos AK (2009) SoftCuts: A soft edge smoothness prior for color image super-resolution. IEEE Trans Image Process 18(5):969–981
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database, Computer Vision and Pattern Recognition 2009. CVPR 2009. IEEE Conference on, pp. 248-255
Dong C, Loy CC, He K, et al. (2014) Learning a deep convolutional network for image super-resolution[C]//European Conference on Computer Vision. Springer, Cham, 184-199
Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network[C]//European Conference on Computer Vision. Springer, Cham, 391-407
He K, Zhang X, Ren S et al. (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE international conference on computer vision. 1026-1034
He K, Zhang X, Ren S et al. (2016) Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 770-778
Huang J, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
Huang G, Liu Z, Weinberger KQ et al (2017) Densely connected convolutional networks[C]. Proc IEEE Conf Comput Vis Pattern Recognit 1(2):3
Hung KW, Siu WC (2012) Robust soft-decision interpolation using weighted least squares. IEEE Trans Image Process 21(3):1061–1069
Hung KW, Siu WC (2012) Single image super-resolution using iterative Wiener filter, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Kyoto, Japan, Mar. 1269-1272
Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of gans for improved quality, stability, and variation. submitted to ICLR 2018
Kim J, Kwon LJ, Mu LK (2016) Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1646-1654
Kim J, Kwon LJ, Mu LK (2016) Deeply-recursive convolutional network for image super-resolution[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 1637-1645
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980.
Lai WS, Huang JB, Ahuja N, et al. (2017) Deep laplacian pyramid networks for fast and accurate super-resolution[C]//Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 624-632
Ledig C, Theis L, Husz` ar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et al. (2016) Photo-realistic single image super-resolution using a generative adversarial network. arXiv:1609.04802
Lim B, Son S, Kim H et al. (2017) Enhanced deep residual networks for single image super-resolution[C]//The IEEE conference on computer vision and pattern recognition (CVPR) workshops. 1(2): 4.
Liu H, Feng Y, Li L (2010) Multi-channel fast super-resolution image reconstruction based on matrix observation model[J]. J Harbin Inst Techn 17(2):239–246
Mao X, Shen C, Yang Y-B Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In NIPS 2016
Marquina A, Osher SJ (2008) Image super-resolution by TV-regularization and Bregman iteration. J Sci Comput 37(3):367–382
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[C]//Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. IEEE, 2: 416-423
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 234-241
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3791-3799.
Shi W, Caballero J, Ledig C, Zhuang X, Bai W, Bhatia K, Marvao AMSM de, Dawes T, ORegan D, Rueckert D (2013) Cardiac image super-resolution with global correspondence using multi-atlas patchmatch. In MICCAI
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In CVPR
Tai Y, Yang J, Liu X et al. (2017) Memnet: A persistent memory network for image restoration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4539-4547
Timofte R, De SV, Van GL (2014) A+: Adjusted anchored neighborhood regression for fast super-resolution[C]//Asian Conference on Computer Vision. Springer, Cham, 111-126
Timofte R, Agustsson E, Van Gool L, Yang M-H, Zhang L, Lim B, Son S, Kim H, Nah S, Lee KM et al. (2017) Ntire 2017 challenge on single image super-resolution: Methods and results. In CVPRW
Tong T, Li G, Liu X et al. (2017) Image Super-Resolution Using Dense Skip Connections[C]//2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 4809-4817
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Wang Y, Liu Q, Zhou H, Wang Y (2018) Learning multi-denoising autoencoding priors for image super-resolution. J Vis Commun Image Represent 57:152–162
Xu R, Zhang J, Huang K (2016) Image super-resolution using two-channel convolutional neural networks[J]. J Image Graph 21(5):556–564
Yang CY, Yang MH (2013) Fast direct super-resolution by simple functions[C]//Computer Vision (ICCV), 2013 IEEE International Conference on. IEEE, 561-568.
Yang J, Wright J, Huang T, et al. (2008) Image super-resolution as sparse representation of raw image patches[C]//Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 1-8
Yang J, Wright J, Huang TS et al (2010) Image super-resolution via sparse representation[J]. IEEE Trans Image Process 19(11):2861–2873
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In Proceedings of the International Conference on Curves and Surfaces
Zhang K, Zuo W, Zhang L (2018) Learning a single convolutional super-resolution network for multiple degradations, in Proc. IEEE Conf. Comput. Vis. Pattern Recog.
Zhao Y, Wang RG, Jia W, Wang W-M, Gao W (2017) Iterative projection reconstruction for fast and efficient image upsampling. Neurocomputing 226:200–211
Zou W, Yuen PC (2012) Very low resolution face recognition problem[J]. IEEE Trans Image Process 21(1):327–340
Acknowledgements
The authors sincerely thank the anonymous reviewers for their valuable comments and constructive suggestions that are very helpful in the improvement of this paper. This work was supported in part by the National Natural Science Foundation of China under 61661028, 61871206, 61661031, 61463035, and the Natural Science Foundation of Jiangxi Province (20181BAB202003).
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
Yang, Y., Liu, Q., Zhang, M. et al. Bi-path network coupling for single image super-resolution. Multimed Tools Appl 78, 21981–21998 (2019). https://doi.org/10.1007/s11042-019-7511-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-7511-x