Complementing SRCNN by Transformed Self-Exemplars

  • Andreas AakerbergEmail author
  • Christoffer B. RasmussenEmail author
  • Kamal NasrollahiEmail author
  • Thomas B. MoeslundEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10165)


Super-resolution algorithms are used to improve the quality and resolution of low-resolution images. These algorithms can be divided into two classes of hallucination- and reconstruction-based ones. The improvement factors of these algorithms are limited, however, previous research [9, 10] has shown that combining super-resolution algorithms from these two different groups can push the improvement factor further. We have shown in this paper that combining super-resolution algorithms of the same class can also push the improvement factor up. For this purpose, we have combined two hallucination based algorithms, namely the one found in Single Image Super-Resolution from Transformed Self-Exemplars [7] and the Super-Resolution Convolutional Neural Network from [4]. The combination of these two, through an alpha-blending, has resulted in a system that outperforms state-of-the-art super-resolution algorithms on public benchmark datasets.


Super-Resolution Convolutional Neural Network Self-Exemplars 


  1. 1.
    Martinez, A.M., Benavente, R.: The AR face database. CVC Technical report 24. Accessed 27 April 2016
  2. 2.
    Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: British Machine Vision Conference, BMVC 2012, Surrey, UK, 3–7 September 2012, pp. 1–10 (2012).
  3. 3.
    Dai, D., Wang, Y., Chen, Y., Gool, L.J.V.: How useful is image super-resolution to other vision tasks? CoRR abs/1509.07009 (2015).
  4. 4.
    Dong, C., Loy, C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)CrossRefGoogle Scholar
  5. 5.
    Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980). CrossRefzbMATHGoogle Scholar
  6. 6.
    Gerchberg, R.W.: Super-resolution through error energy reduction. J. Mod. Opt. 22(8), 709–720 (1974)Google Scholar
  7. 7.
    Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  8. 8.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of 8th International Conference Computer Vision, vol. 2, pp. 416–423, July 2001Google Scholar
  9. 9.
    Nasrollahi, K., Escalera, S., Rasti, P., Anbarjafari, G., Baro, X., Escalante, H.J., Moeslund, T.B.: Deep learning based super-resolution for improved action recognition. In: 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 67–72, November 2015Google Scholar
  10. 10.
    Nasrollahi, K., Moeslund, T.B.: Finding and improving the key-frames of long video sequences for face recognition. In: Fourth IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS) 2010, pp. 1–6 (2010)Google Scholar
  11. 11.
    Nasrollahi, K., Moeslund, T.: Super-resolution: a comprehensive survey. Mach. Vis. Appl. 25(6), 1423–1468 (2014)CrossRefGoogle Scholar
  12. 12.
    Vieira, T.F., Bottino, A., Laurentini, A., De Simone, M.: Detecting siblings in image pairs. Vis. Comput. 30(12), 1333–1345 (2014). 10.1007/s00371-013-0884-3 CrossRefGoogle Scholar
  13. 13.
    Wang, Z., Bovik, A.C.: Mean squared error: love it or leave it? A new look at signal fidelity measures. IEEE Sig. Process. Mag. 26(1), 98–117 (2009)CrossRefGoogle Scholar
  14. 14.
    Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Proceedings of the 7th International Conference on Curves and Surfaces, pp. 711–730 (2012).

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Visual Analysis of People (VAP) LaboratoryAalborg UniversityAalborgDenmark

Personalised recommendations