Advertisement

Deep CNN for Single Image Super Resolution Using Skip Connections

  • Sathisha BasavarajuEmail author
  • Smriti Bahuguna
  • Sibaji Gaj
  • Arijit Sur
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11941)

Abstract

With the current progress in deep learning domain, quite a few deep learning based models have been developed to address the challenges of Single Image Super Resolution (SISR) task. Recent trend in SISR models is towards increasing the depth of the model to achieve a high accuracy through multiple contexts learned at various depth of the network. Skip connections between different layers of the deep network help in utilising multi-context features and also help to address the issue of vanishing gradients but at the cost of increased computational complexity. In this paper, a deep CNN with a minimum number of skip connections is devised to derive a High-Resolution (HR) image from a Low-Resolution (LR) image. A detailed experimental analysis is carried out on skip connection parameters for a given depth to optimise network parameters. The proposed model gives better results compared to existing methods for multiple scales on benchmark data-sets.

Keywords

Residual learning Skip connections Single image super resolution Deep learning 

References

  1. 1.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. PAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012)Google Scholar
  3. 3.
    Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10593-2_13CrossRefGoogle Scholar
  4. 4.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on CVPR, pp. 2261–2269. IEEE (2017)Google Scholar
  5. 5.
    Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on CVPR, pp. 5197–5206 (2015)Google Scholar
  6. 6.
    Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on CVPR, pp. 1646–1654 (2016)Google Scholar
  7. 7.
    Kim, J., Kwon Lee, J., Mu Lee, K.: Deeply-recursive convolutional network for image super-resolution. In: Proceedings of the IEEE Conference on CVPR, pp. 1637–1645 (2016)Google Scholar
  8. 8.
    Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Deep Laplacian pyramid networks for fast and accurate super-resolution. In: IEEE Conference on CVPR, vol. 2, p. 5 (2017)Google Scholar
  9. 9.
    Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Fast and accurate image super-resolution with deep Laplacian pyramid networks. IIEEE Trans. PAMI (2018)Google Scholar
  10. 10.
    Lim, B., Son, S., Kim, H., et al.: Enhanced deep residual networks for single image super-resolution. In: The IEEE Conference on CVPR Workshops, vol. 1, p. 4 (2017)Google Scholar
  11. 11.
    Schulter, S., Leistner, C., Bischof, H.: Fast and accurate image upscaling with super-resolution forests. In: Proceedings of the IEEE Conference on CVPR, pp. 3791–3799 (2015)Google Scholar
  12. 12.
    Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: 2017 IEEE Conference on CVPR, pp. 2790–2798. IEEE (2017)Google Scholar
  13. 13.
    Tai, Y., Yang, J., Liu, X., Xu, C.: MemNet: a persistent memory network for image restoration. In: Proceedings of the IEEE Conference on CVPR, pp. 4539–4547 (2017)Google Scholar
  14. 14.
    Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: ICCV, pp. 4809–4817. IEEE (2017)Google Scholar
  15. 15.
    Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  16. 16.
    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_47CrossRefGoogle Scholar
  17. 17.
    Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep CNN denoiser prior for image restoration. In: IEEE Conference on CVPR, vol. 2 (2017)Google Scholar
  18. 18.
    Zhang, K., Zuo, W., Zhang, L.: Learning a single convolutional super-resolution network for multiple degradations. In: IEEE Conference on CVPR, vol. 6 (2018)Google Scholar
  19. 19.
    Zhang, K., Gao, X., Tao, D., et al.: Single image super-resolution with non-local means and steering kernel regression. Image 11, 12 (2012)zbMATHGoogle Scholar
  20. 20.
    Zhang, L., Wu, X.: An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans. Image Process. 15(8), 2226–2238 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Sathisha Basavaraju
    • 1
    Email author
  • Smriti Bahuguna
    • 1
  • Sibaji Gaj
    • 1
  • Arijit Sur
    • 1
  1. 1.Indian Institute of Technology GuwahatiGuwahatiIndia

Personalised recommendations