Abstract
This paper proposes a new model for single image super-resolution (SR) task by utilizing the design of densely connected convolutional networks (DenseNet). The proposed method is an end-to-end model which is able to learn mapping between low- and high-resolution images. The proposed method takes the low-resolution images as input and generates its high-resolution version. Unlike those conventional methods which adjust each component of convolutional networks separately, our model jointly optimizes all layers. Besides, the proposed model has a lightweight structure and is extensively evaluated on widely adopted data sets. In our experiments, the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively. In addition, we also carried out experiments in terms of different designs and configurations to achieve better balance between reconstruction performance and speed in this paper.







Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. In: Proceedings of IEEE international conference on computer vision. Kyoto, pp 349–356
Dai D, Timofte R, Van Gool L (2015) Jointly optimized regressors for image super-resolution. Comput Graph Forum 34(2):95–104
Freedman G, Fattal R (2011) Image and video upscaling from local selfexamples. ACM Trans Graphs (TOG) 30(2):12
Chang H, Yeung DY, Xiong Y (2004) Super resolution through neighbor embedding. In: Proceedings of the 2004 IEEE Computer society conference on IEEE computer vision and pattern recognition, vol 1, no 1. Washington, DC, pp 1–1
Cui Z, Chang H, Shan S, Zhong B, Chen X (2014) Deep network cascade for image super-resolution. European conference on computer vision. Springer, Cham, pp 49–64
Bevilacqua M, Roumy A, Guillemot C, Morel MLA (2012) Low-complexity single-image super- resolution based on nonnegative neighbor embedding. In: Proc Brit Mach vis conf, pp 1–10
Yang C-Y, Yang M-H (2013) Fast direct super-resolution by simple functions. In: Proceedings of IEEE International conference on computer vision. Sydney, pp 561–568
Freeman WT, Pasztor EC, Carmichael OT (2000) Learning lowlevel vision. Int J Comput Vis 40 (1):25–47
Freeman WT, Jones TR, Pasztor EC (2002) Example-based superresolution. IEEE Comput Graph Appl 22(2):56–65
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: International conference on curves and surfaces. Springer, Berlin, pp 711–730
Schulter S, Lesistner C, Bischof H (2015) Fast and accutate image upscaling with super-resulution forests. In: Proceedings of IEEE Conference on computer vision and pattern recognition, pp 184–199
Yang CY, Ma C, Yang MH (2014) Single-image super-resolution: Abenchmark. In: European Conference on computer vision. Springer, Cham, pp 372–386
Freeman WT, Pasztor EC, Carmichael OT (2000) Learning low-level vision. Int J Comput Vis 40 (11):25–47
Huang JJ, Siu WC, Liu TR (2015) Fast image interpolation via random forests. IEEE Trans Image Process 24(10):3232–3245
Salvador J, PerezPellitero E (2015) Naive Bayes super-resulution forest. In: Proceedings of IEEE International conference on computer vision, pp 325–333
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: Proc IEEE Conf Comput vis pattern recognit, pp 5197–5206
Yang J, Lin Z, Cohen S (2013) Fast image super-resolution based on in-place example regression. In: 2013 IEEE Conference on IEEE computer vision and pattern recognition (CVPR), pp 1059–1066
Timofte R, De Smet V, Van Gool L (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Asian Conference on computer vision. Springer, Cham, pp 111–126
Jia K, Wang X, Tang X (2013) Image transformation based on learning dictionaries across image spaces. IEEE Trans Pattern Anal Mach Intell 35(11):367–380
Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super resolution. IEEE Trans Image Process 21(8):3467–3478
Kim KI, Kwon Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE Trans Pattern Anal Mach Intell 32(6):1127–1133
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 3791–3799
Timofte R, Smet V, Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. In: Proceedings of IEEE International conference on computer vision, pp 1920–1927
Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: Proceedings of European conference on computer vision, pp 184–199
Dong C, Loy CC, He K (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Zeyde R, Elad M, Protter M (2012) On single image scale-up using sparse-representations. In: Proc. 7th Int Conf curves surfaces, pp 711–730
Yang J, Wright J, Huang T, Ma Y (2008) Image super-resolution as sparse representation of raw image patches. In: Proc IEEE Conf comput vis pattern recog, pp 1–8
Shi W, Caballero J, Huszar F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video superresolution using an efficient sub-pixel convolutional neural network. In: Proceedings of IEEE Conference on computer vision and pattern recognition, pp 1874–1883
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of IEEE Conference on computer vision and pattern recognition. arXiv:http://arXiv.org/abs/1511.04587
Keys RG (1981) Cubic convolution interpolation for digital image processing. IEEE Trans Acoust Speech Signal Process 29(6):1153–1160
Wang Z, Liu D, Yang J, Han W, Huang T (2015) Deep networks for image super-resolution with sparse prior. In: Proceedings of IEEE International conference on computer vision, pp 370–378
Duchon CE (1979) Lanczos filtering in one and two dimensions. J Appl Meteorol 18(8):1016–1022
Sun J, Sun J, Xu Z, Shum H-Y (2008) Image super-resolution using gradient profile prior. In: Proceedings of IEEE Conference on computer vision and pattern recognition, pp 1–8
Protter M, Elad M, Takeda H, Milanfar P (2009) Generalizing the nonlocal-means to super-resolution reconstruction. IEEE Trans Image Process 18(1):36–51
Zhang K, Gao X, Tao D, Li X (2012) Single image super-resolution with non-local means and steering kernel regression. IEEE Trans Image Process 21(11):4544–4556
Baker S, Kanade T (2000) Limits on super-resolution and how to break them[J]. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183
Gu S, Zuo W, Xie Q, Meng D, Feng X, Zhang L (2015) Convolutional sparse coding for image super-resolution. In: Proceedings of IEEE International conference on computer vision, pp 1823–1831
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 IEEE International conference on computer vision, vol 2, pp 416–423
Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel M-L (2012) Lowcomplexity single-image super-resolution based on nonnegative neighbor embedding, 1–10
He K, Sun J (2015) Convolutional neural networks at constrained time cost. In: Proc IEEE Conf comput vis pattern recog, pp 379–3799
Wang D, Li M (2017) Deep stochastic configuration networks with universal approximation property. arXiv:http://arXiv.org/abs/1702.05639
Jaderberg M, Dalibard V, Osindero S, et al. (2017) Population based training of neural networks. arXiv:http://arXiv.org/abs/1711.09846
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kuang, P., Ma, T., Chen, Z. et al. Image super-resolution with densely connected convolutional networks. Appl Intell 49, 125–136 (2019). https://doi.org/10.1007/s10489-018-1234-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-018-1234-y