Advertisement

Efficient Single Image Super Resolution Using Enhanced Learned Group Convolutions

  • Vandit JainEmail author
  • Prakhar Bansal
  • Abhinav Kumar Singh
  • Rajeev Srivastava
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)

Abstract

Convolutional Neural Networks (CNNs) have demonstrated great results for the single-image super-resolution (SISR) problem. Currently, most CNN algorithms promote deep and computationally expensive models to solve SISR. However, we propose a novel SISR method that uses relatively less number of computations. On training, we get group convolutions that have unused connections removed. We have refined this system specifically for the task at hand by removing unnecessary modules from original CondenseNet. Further, a reconstruction network consisting of deconvolutional layers has been used in order to upscale to high resolution. All these steps significantly reduce the number of computations required at testing time. Along with this, bicubic upsampled input is added to the network output for easier learning. Our model is named SRCondenseNet. We evaluate the method using various benchmark datasets and show that it performs favourably against the state-of-the-art methods in terms of both accuracy and number of computations required.

Keywords

Convolutional Neural Networks Deep learning Image super resolution Learned group convolutions 

Notes

Acknowledgements

The authors are grateful to HP Inc. for their support to the Innovations Incubator Program. They are thankful to other stakeholders of this program including Leadership, and Faculty Mentors at IIT-BHU, Drstikona and Nalanda Foundation. Authors are also grateful to Dr. Prasenjit Banerjee, Nalanda Foundation for his mentoring and support

References

  1. 1.
    Huang, G., Liu, S., Maaten, L.V.D., Weinberger, K.Q.: CondenseNet: an efficient DenseNet using learned group convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  2. 2.
    Duchon, C.E.: Lanczos filtering in one and two dimensions. J. Appl. Meteorol. 18(8), 1016–1022 (1979)CrossRefGoogle Scholar
  3. 3.
    Schulter, S., Leistner, C., Bischof, H.: Fast and accurate image upscaling with super-resolution forests. In: Conference on Computer Vision (2015)Google Scholar
  4. 4.
    Timofte, R., De Smet, V., Van Gool, L.: A+: adjusted anchored neighborhood regression for fast super-resolution. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 111–126. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16817-3_8CrossRefGoogle Scholar
  5. 5.
    Perez-Pellitero, E., Salvador, J., Ruiz-Hidalgo, J., Rosenhahn, B.: PSyCo: manifold span reduction for super resolution. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  6. 6.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: International Conference on Computer Vision (2009)Google Scholar
  7. 7.
    Yang, J., Wright, J., Huang, T., Ma, Y.: Image superresolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Salvador, J., Perez-Pellitero, E.: Naive bayes superresolution forest. In: International Conference on Computer Vision (2015)Google Scholar
  9. 9.
    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
  10. 10.
    Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_25CrossRefGoogle Scholar
  11. 11.
    Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Computer Vision and Pattern Recognition, pp. 1646–1654 (2016)Google Scholar
  12. 12.
    Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image SuperResolution. In: Computer Vision and Pattern Recognition, pp. 1637–1645 (2016)Google Scholar
  13. 13.
    Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105–114 (2017)Google Scholar
  14. 14.
    Sajjadi, M.S.M., Schlkopf, B., Hirsch, M.: EnhanceNet: single image super-resolution through automated texture synthesis. In: IEEE International Conference on Computer Vision (ICCV), Venice, pp. 4501–4510 (2017)Google Scholar
  15. 15.
    Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: The IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  16. 16.
    Lim, B., Son, S., Kim, H., Nah, S., Lee, K. M.: Enhanced deep residual networks for single image super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1132–1140 (2017)Google Scholar
  17. 17.
    Cheng, X., Li, X., Tai, Y., Yang, J.: SESR: single image super resolution with recursive squeeze and excitation networks. In: International Conference on Pattern Recognition (ICPR) (2018)Google Scholar
  18. 18.
    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 Computer Vision and Pattern Recognition (2017)Google Scholar
  19. 19.
    Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2790–2798 (2017)Google Scholar
  20. 20.
    Tai, Y., Yang, J., Liu, X., Xu, C.: MemNet: a persistent memory network for image restoration. In: IEEE International Conference on Computer Vision (ICCV), Venice, pp. 4549–4557 (2017)Google Scholar
  21. 21.
    Shi, W., et al.: 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), pp. 1874–1883 (2016)Google Scholar
  22. 22.
    Nah, S., Kim, T.H., Lee., K.M.: Deep multi-scale convolutional neural network for dynamic scene deblurring. arXiv preprint arXiv:1612.02177 (2016)
  23. 23.
    Hayat, K.: Super-Resolution via Deep Learning (2017). arXiv:1706.09077
  24. 24.
    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
  25. 25.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  26. 26.
    Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity SingleImage super-resolution based on nonnegative neighbor embedding. In: British Machine Vision Conference (2012)Google Scholar
  27. 27.
    Zeyde, R., Elad, M., Protter, M.: Low-complexity SingleImage super-resolution based on nonnegative neighbor embedding. In: International Conference on Curves and Surfaces, pp. 711–730 (2012)CrossRefGoogle Scholar
  28. 28.
    Huang, J.B., Singh, A., Ahuja, N.: Single image superresolution from transformed self-exemplars. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  29. 29.
    Kingma, D., Adam, J.B.: A method for stochastic optimization. In: International Conference on Learning Representations, ICLR (2015)Google Scholar
  30. 30.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Vandit Jain
    • 1
    Email author
  • Prakhar Bansal
    • 1
  • Abhinav Kumar Singh
    • 1
  • Rajeev Srivastava
    • 1
  1. 1.Indian Institute of Technology (Banaras Hindu University)VaranasiIndia

Personalised recommendations