Abstract
Single image super-resolution (SR) models which based on convolutional neural network mostly use chained stacking to build the network. It ignores the role of hierarchical features and relationship between layers, resulting in the loss of high-frequency components. To address these drawbacks, we introduce a novel multipath feedforward network (MFNet) based on staged feature fusion unit (SFF). By changing the connection between networks, MFNet strengthens the inter-layer relationship and improves the information flow in the network, thereby extracting more abundant high-frequency components. Firstly, SFF extracts and integrates hierarchical features by dense connection, which expands the information flow of the network. Afterwards, we use adaptive method to learn effective features in hierarchical features. Then, in order to strengthen relationship between layers and fully use the hierarchical features, we use multi-feedforward structure to connect each SFF, which enables multipath feature re-usage and explores more abundant high-frequency components on this basis. Finally, the image reconstruction is realized by combining the shallow features and the global residual. Extensive benchmark evaluation shows that the performance of MFNet has a significant improvement over the state-of-the-art methods.
Similar content being viewed by others
References
Bevilacqua M, Roumy A, Guillemot C, Morel M-A (2012) Low-complexity single image super-resolution based on nonnegative neighbor embedding. In: British Machine Vision Conference (BMVC). 1–10
Chen Y, Li J, Xiao H, Jin X, Yan S, Feng J (2017) Dual path networks. In: Neural Information Processing Systems (NIPS). 4467–4475
Cheong JY, Park IK (2017) Deep CNN-based super-resolution using external and internal examples. IEEE Sig Proc Lett 24(8):1252–1256
Cho D, Tai YW, KweonI (2016) Natural image matting using deep convolutional neural networks. In: European Conference on Computer Vision (ECCV). 626–643
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
Dong C, Chen CL, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European Conference on Computer Vision (ECCV). 184–199
Dong C, Chen CL, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Dong C, Chen CL,Tang X (2016) Accelerating the super-resolution convolutional neural network. In: European Conference on Computer Vision (ECCV). 391–407
Gregor K, Yann L (2010) Learning fast approximations of sparse coding. In: International Conference on Machine Learning (ICML). 399–406
Gu S, Zuo W, Xie Q, Meng D, Feng X,Zhang L (2015) Convolutional sparse coding for image super resolution. In: IEEE Int Conf Comput Vis (ICCV). 1823–1831
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE Int Conf Comput Vis (ICCV). 1026–1034
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conf Comput Vis Patt Recog (CVPR). 770–778
Huang J-B, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. IEEE Conf Comput Vis Patt Recog (CVPR):5197–5206
Huang G, Liu Z, Weinberger KQ, Maaten L-vd (2017) Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2261–2269
Kim J, Lee JK, Lee KM (2016) Deeply-recursive convolutional network for image super-resolution. IEEE Conf Comput Vis Patt Recog (CVPR):1637–1645
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: IEEE Conf Comput Vis Patt Recog (CVPR). 1646–1654
Lai W, Huang J, Ahuja N, Yang M (2017) Deep laplacian pyramid networks for fast and accurate super-resolution. In: IEEE Conf Comput Vis Patt Recog (CVPR). 5835–5843
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: IEEE Conf Comput Vis Patt Recog (CVPR). 105–114
Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10(10):1521–1527
Li S, Fan R, Lei G, Hou G (2018) A two-channel convolutional neural network for image super-resolution. Neurocomputing 275:267–277
Mao X, Shen C, Yang Y (2016) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Neural Information Processing Systems (NIPS). 2802–2810
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 Eighth IEEE International Conference on Computer Vision. 416–423
Qian N (1999) On the momentum term in gradient descent learning algorithms. Neural Netw 12(1):145–151
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. In:IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3791–3799
Shi W, Caballero J, Huszar F, Totz J, Aitken A-P, Bishop R, Rueckert D, Wang Z (2016) Real-Time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1874–1883
Shi W, Jiang F, Zhao D (2017) Single image super-resolution with dilated convolution based multi-scale information learning inception module. In: IEEE International Conference on Image Processing (ICIP). 977–981
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR)
Sun J, Sun J, Xu Z, Shum H (2008) Image super-resolution using gradient profile prior. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1–8
SzegedyC LW, Jia Y, Sermanet P, Reed S (2015) Going deeper with convolutions. IEEE Conf Comput Vis Patt Recog (CVPR):1–9
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: IEEE Conf Comput Vis Patt Recog (CVPR). 2790–2798
Tai Y, Yang Y, Liu X, Xu C (2017) MemNet: A persistent memory network for image restoration. In: IEEE Int Conf Comput Vis (ICCV). 4549–4557
Tang Y, Chen H, Liu Z, Song B, Wang Q (2016) Example-based super-resolution via social images. Neurocomputing 172:38–47
Timofte R, De V, Gool LV (2013) Anchored neighborhood regression for fast example-based super-resolution. In: Proc IEEE International Conference on Computer Vision (ICCV). 1920–1927
Timofte R, De V, Gool LV (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Proc. Asian Conference on Computer Vision (ACCV), pp 111–126
Wang Q, Yuan Y (2014) High quality image resizing [J]. Neurocomputing 131:348–356
Wang Z, Yang Y, Wang Z, Chang S, Han W, Yang J, Huang T (2015) Self-tuned deep super resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1–8
Wang Z, Liu D, Wen B, Yang J, Han W, Huang T-S (2015) Deep networks for image super-resolution with sparse prior. In: IEEE Int Conf Comput Vis (ICCV). 370–378
Wang Y, Wang L, Wang H, Li P (2016) End-to-End image super resolution via deep and shallow convolutional networksarXiv preprint arXiv:1607.07680
Xu J, Zhao Y, Dong Y, Bai H (2017) Fast and accurate image super-resolution using a combined loss. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1093–1099
Xu J, Chae Y, Stenger B (2017) BYNET-SR: Image super resolution with a bypass connection network. In: IEEE International Conference on Image Processing (ICIP). 4053–4057
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: Proceedings of the 7th International Conference on Curves and Surfaces. 711–730
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
Zhang K, Zuo W, Gu S, Zhang L (2017) Learning deep CNN denoiser prior for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2808–2817
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian Denoiser: residual learning of deep CNN for image Denoising. IEEE Trans Image Process 26(7):3142–3155
Acknowledgements
We express our sincere thanks to the anonymous reviewers for their helpful comments and suggestions to raise the standard of our paper.
Funding
This study was funded by the National Natural Science Foundation of China under (grant number 61672202).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The whole authors are fulltime teachers of Hefei University of Technology besides the second author Pengfei Yu, and he is the fulltime student of Hefei University of Technology. The whole authors declare that we have no conflicts of interest 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
About this article
Cite this article
Shen, M., Yu, P., Wang, R. et al. Multipath feedforward network for single image super-resolution. Multimed Tools Appl 78, 19621–19640 (2019). https://doi.org/10.1007/s11042-019-7334-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-7334-9