Advertisement

MSCE: An Edge-Preserving Robust Loss Function for Improving Super-Resolution Algorithms

  • Ram Krishna PandeyEmail author
  • Nabagata Saha
  • Samarjit Karmakar
  • A. G. Ramakrishnan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)

Abstract

With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques. In this work, we propose a robust loss function based on the preservation of edges obtained by the Canny operator. This loss function, when combined with the existing loss function such as mean square error (MSE), gives better SR reconstruction measured in terms of PSNR and SSIM. Our proposed loss function guarantees improved performance on any existing algorithm using MSE loss function, without any increase in the computational complexity during testing.

Keywords

Loss function CNN GAN Super-resolution Mean square error Mean square Canny error Edge preservation PSNR SSIM 

References

  1. 1.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: 12th IEEE International Conference on Computer Vision, pp. 349–356 (2009)Google Scholar
  2. 2.
    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
  3. 3.
    Shi, W., Caballero, J., Husz, F., Totz, J., Aitken, A. P., Bishop, R., Rueckert, D., Wang, Z.: 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, pp. 1874–1883 (2016)Google Scholar
  4. 4.
    Pandey, R.K., Ramakrishnan, A.G.: A Hybrid Approach of Interpolations and CNN to Obtain Super-Resolution. arXiv preprint arXiv:1805.09400 (2018)
  5. 5.
    Pandey, R.K., Ramakrishnan, A.G.: Language independent single document image super-resolution using CNN for improved recognition. arXiv preprint arXiv:1701.08835 (2017)
  6. 6.
    Pandey, R.K., Ramakrishnan, A.G.: Sadhana 43, 15 (2018).  https://doi.org/10.1007/s12046-018-0794-1
  7. 7.
    Pandey, R.K., Maiya, S.R., Ramakrishnan, A.G.: A new approach for upscaling document images for improving their quality. In: 14th International IEEE India Conference INDICON 2017, IIT Roorkee, 15–17 December (2017)Google Scholar
  8. 8.
    Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  9. 9.
    Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_43CrossRefGoogle Scholar
  10. 10.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)Google Scholar
  11. 11.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986)CrossRefGoogle Scholar
  12. 12.
    Simonyan, K., Vedaldi, A. Zisserman, A.: Deep inside convolutional net-works: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
  13. 13.
    Gatys, L.A., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: Advances in Neural Information Processing Systems 28 (2015)Google Scholar
  14. 14.
    Gatys, L.A., Ecker, A.S., Bethge, M.: a neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)
  15. 15.
    Pandey, R.K., Karmakar, S., Ramakrishnan, A.G.: Computationally efficient approaches for image style transfer. arXiv preprint arXiv:1807.05927 (2018)
  16. 16.
    Kinga, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)Google Scholar
  17. 17.
    Agustsson, E., Timofte, R.: NTIRE 2017 challenge on single image super-resolution: dataset and study. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2017)Google Scholar
  18. 18.
    Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the BMVC (2012)Google Scholar
  19. 19.
    Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Proceedings of the International Conference Curves and Surfaces, Avignon-France (2010)Google Scholar
  20. 20.
    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 the 8th International Conference on Computer Vision, vol. 2, pp. 416–423 (2001)Google Scholar
  21. 21.
    Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5197–5206 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Ram Krishna Pandey
    • 1
    Email author
  • Nabagata Saha
    • 2
  • Samarjit Karmakar
    • 2
  • A. G. Ramakrishnan
    • 1
  1. 1.Department of Electrical EngineeringIndian Institute of ScienceBangaloreIndia
  2. 2.Department of Computer Science and EngineeringNIT WarangalWarangalIndia

Personalised recommendations