Skip to main content
SpringerLink
Log in

Towards realistic image via function learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

There has been a remarkable growth in computer vision due to the introduction of deep convolutional neural network. In most electronic imaging applications, images with high resolution are desired and cannot be ignored in many crucial applications. Super-resolution is a technique that enhances the resolution of images from the low-resolution input. Even thought, the performance of pattern recognition in computer vision will be improved if high resolution image is provided. The current super-resolution models based convolutional neural network has shown great performance, and also could outpace the other models. Depth in of CNN models is crucial importance for image super-resolution. However, the deeper networks based SR techniques are more difficult to train. To address these problems we propose a very deep residual network which comprises residual in residual structure to form a very deep network. In particular, the proposed model consists of several residual units with long skip connection. The proposed model allows low-frequency information to be bypassed through multiple skip connections, and the high-frequency information will be centralized in the main network. Extensive experiments show that our proposed model achieves better performance against state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Lev-enberg J, Man_e D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Vi_egas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) Tensorflow: large-scale machine learning on heterogeneous systems. Software available from tensorow.org

  2. Burger HC, Schuler CJ, Harmeling S (2012) Image denoising: can plain neural networks compete with bm3d? In CVPR

  3. Cui Z, Chang H, Shan S, Zhong B, Chen X (2014) Deep network cascade for image super-resolution. Springer International Publishing, Cham, pp 49–64

    Google Scholar 

  4. Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. TPAMI 38(2):295–307

    Article  Google Scholar 

  5. Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. In: European Conference on Computer Vision

  6. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proc IEEE Conf Comp Vis Patt Recogn

  7. Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507

  8. Kim J, Lee JK, Lee KM (2015) Accurate image super-resolution using very deep convolutional networks. arXiv preprint arXiv:1511.04587

  9. Kim J, Lee JK, Lee KM (2015) Deeply-recursive convolutional network for image super-resolution. arXiv preprint arXiv:1511.04491

  10. Kingma D, Ba J (2014) Adam: a method for stochastic optimization. In: ICLR

  11. Ledig C, Theis L, Husźar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2017) Photo-realistic single image superresolution using a generative adversarial network. In: CVPR

  12. Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: CVPRW

  13. Mao XJ, Shen C, Yang YB (2016) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Neural Inf Proces Syst

  14. Shamsolmoali P, Zareapoor M, Jain DK et al (2018) Deep convolution network for surveillance records super-resolution. Multimed Tools Appl. https://doi.org/10.1007/s11042-018-5915-7

  15. Shamsolmoali P, Zareapoor M, Yang J Convolutional Neural Network in Network (CNNiN): hyperspectral image classification and dimensionality reduction. IET Image Process. https://doi.org/10.1049/iet-ipr.2017.1375

  16. Shi W, Caballer J, Huszar F et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proc IEEE Conf Comput Vis Pattern Recognit 1:1874–1883

    Google Scholar 

  17. Tai Y, Yang J, Liu X, Xu C (2017) Memnet: a persistent memory network for image restoration. In: ICCV

  18. Timofte R, Agustsson E, Van Gool L, Yang MH, 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

  19. Tsai RY, Huang TS (1984) Multi-frame image restoration and registration. Adv Comput Vis Image Process 1:317–339

    Google Scholar 

  20. Wang Y, Wang L, Wang H, Li P (2016) End-to-end image superresolution via deep and shallow convolutional networks. arXiv preprint arXiv:1607.07680

  21. Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. In NIPS

  22. Yang W, Feng J, Yang J et al (2016) Deep edge guided recurrent residual learning for image super-resolution. arXiv preprint arXiv:1604.08671

  23. Zareapoor M, Shamsolmoali P, Kumar DJ, Wang H, Yang J (2017) Kernelized support vector machine with deep learning: an efficient approach for extreme multiclass dataset. Pattern Recogn Lett 115(2018):4–13

    Google Scholar 

  24. Zareapoor M, Shamsolmoali P, Yang J (2018) Learning depth super-resolution by using multi-scale convolutional network. J Intell Fuzzy Syst. https://doi.org/10.3233/JIFS-18136

  25. Zareapoor M, Kumar JD, Yang J (2018) Local spatial information for image super-resolution. Cogn Syst Res 52:49–57

    Article  Google Scholar 

  26. Zeyde R, Elad M, Protter M On single image scale-up using sparse-representations. In Curves and Surfaces, pages 711–730. Springer

  27. Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: CVPR

Download references

Acknowledgements

This research is partly supported by NSFC, China (No: 61572315) and Committee of Science and Technology, Shanghai, China (No: 17JC1403000).

Author information

Authors and Affiliations

  1. Shanghai Jiao Tong University, Shanghai, China

    Masoumeh Zareapoor, Junhao Zhang & Jie Yang

Authors
  1. Masoumeh Zareapoor
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junhao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Masoumeh Zareapoor or Jie Yang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zareapoor, M., Zhang, J. & Yang, J. Towards realistic image via function learning. Multimed Tools Appl 78, 29573–29580 (2019). https://doi.org/10.1007/s11042-019-7361-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-7361-6

Keywords

Search

Navigation