A fast deconvolution-based approach for single-image super-resolution with GPU acceleration

Original Research Paper

Abstract

In this paper, we propose fast deconvolution-based image super-resolution (SR) with graphics processing unit (GPU)-accelerated computation. Recently, the deconvolution-based single-image SR has been proven to be very effective in upsampling images with favorable results. Based on the GPU-accelerated computation, we aim to realize the fast SR reconstruction and achieve balanceable performance in terms of both image quality and computational cost. To achieve this, we provide a novel and efficient deconvolution method to enhance the reconstruction results. We combine the gradient consistency in images with the anisotropic regularization which has been used in motion deblurring. Thus, we produce a directly parallelizable solution which is suitable for running on GPU by minimizing redundancy in computing. Experimental results demonstrate that the proposed method achieves superior performance in comparison with the existing methods with respect to image quality and runtime.

Keywords

Deconvolution Graphics processing unit (GPU) Super-resolution reconstruction Real time Parallelization 

References

  1. 1.
    Tsai, R.Y., Huang, T.: Multiframe image restoration and registration. Adv. Comput. Vis. Image Process. 1, 317–339 (1984)Google Scholar
  2. 2.
    Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. IEEE Signal Process. Mag. 20, 21–36 (2003)CrossRefGoogle Scholar
  3. 3.
    Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example based super-resolution. IEEE Comput. Graphics Appl. 22, 56–65 (2002)CrossRefGoogle Scholar
  4. 4.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: Proceedings of IEEE International Conference on Computer Vision, Kyoto, Japan, pp 349–356. IEEE (2009)Google Scholar
  5. 5.
    Zhang, H., Yang, J., Zhang, Y., Huang, T.: Non-local kernel regression for image and video restoration. In: Proceedings of European Conference on Computer Vision), Heraklion, Crete, Greece, pp 566–579. Springer-Verlag (2010)Google Scholar
  6. 6.
    Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19, 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Tipping, M.E., Bishop, C.M.: Bayesian image super-resolution. In: Proceedings of Neural Information Processing Systems, Vancouver, British Columbia, Canada, pp 1279–1286. MIT Press (2002)Google Scholar
  8. 8.
    Avidan, S., Shamir, A.: Seam carving for content-aware image resizing. ACM Trans. Gr. 26, Article 10 (2007)Google Scholar
  9. 9.
    Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10, 1521–1527 (2001)CrossRefGoogle Scholar
  10. 10.
    Takeda, H., Farsiu, S., Milanfar, P.: Kernel regression for image processing and reconstruction. IEEE Trans. Image Process. 16, 349–366 (2007)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Lin, C.Y., Hsu, C.C., Lin, C.W., Kang, L.W.: Fast deconvolution based image super-resolution using gradient prior. In: Proceedings of Visual Communications and Image Processing, Tainan, Taiwan,  pp 1–4. IEEE (2011)Google Scholar
  12. 12.
    Shan, Q., Li, J., Jia, J., Tang, C.K.: Fast image/video upsampling. ACM Trans. Gr. 27, Article 153 (2008)Google Scholar
  13. 13.
    Dai, S., Han, M., Xu, W., Wu, Y., Gong, Y., Katsaggelos, A.K.: Softcuts: a soft edge smoothness prior for color image super-resolution. IEEE Trans. Image Process. 18, 969–981 (2009)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Sun, J., Sun, J., Xu, Z., Shum, H.Y.: Image super-resolution using gradient profile prior. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, pp 1–8. IEEE (2008)Google Scholar
  15. 15.
    Fattal, R.: Image upsampling via imposed edges statistics. ACM Trans. Gr. 26, Article no. 95 (2007)Google Scholar
  16. 16.
    Tai, Y.W., Liu, S., Brown, M.S., Lin, S.: Super resolution using edge prior and single image detail synthesis. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp 2400–2407. IEEE (2010)Google Scholar
  17. 17.
    Pickup, L.C., Roberts, S.J., Zisserman, A.: A sampled texture prior for image super-resolution. In: Proceedings of Neural Information Processing Systems, Vancouver, British Columbia, Canada, pp 1587–1594. MIT Press (2003)Google Scholar
  18. 18.
    Cohen, Y.H., Fattal, R., Lischinski, D.: Image upsampling via texture hallucination. In: Proceedings of IEEE International Conference on Computational Photography, Cambridge, MA, USA,  pp 1–8. IEEE (2010)Google Scholar
  19. 19.
    Hong, H.Y., Park, I.K.: Single-image motion deblurring using adaptive anisotropic regularization. Opt. Eng. 49, Article 097008 (2010)Google Scholar
  20. 20.
    Owens, D.J., Luebke, D., Govindaraju, N., Harris, M., Kruger, J., Lefohn, E., Aaron, P., Timothy, J.: A survey of general-purpose computation on graphics hardware. Comput. Graphics Forum 26(1), 80–113 (2007)CrossRefGoogle Scholar
  21. 21.
    Gong, M., Langille, A., Gong, M.: Real-time image processing using graphics hardware: a performance study. In: Proceedings of International Conference on Image Analysis and Recognition, Toronto, Canada,  pp 1217–1225. Springer-Verlag (2005)Google Scholar
  22. 22.
    Colic, A., Kalva, H., Furht, B.: Exploring NVIDA-CUDA for video coding. In: Proceedings of the first annual ACM SIGMM conference on Multimedia systems, Phoenix, Arizona, USA,  pp 13–22. ACM (2010)Google Scholar
  23. 23.
    Griebel, M., Zaspel, P.: A multi-GPU accelerated solver for the three dimensional two-phase incompressible Navier-Stokes equations. Comput. Sci. Res. Dev. 25(1–2), 65–73 (2010)CrossRefGoogle Scholar
  24. 24.
    Cheung, N.M., Fan, X., Au, O.C., Kung, M.C.: Video coding on multicore graphics processors. IEEE Signal Process. Mag. 27(2), 79–89 (2010)CrossRefGoogle Scholar
  25. 25.
    Dolan, R., DeSouza, G.: GPU-based simulation of cellular neural networks for image processing. In Proceedings of International Joint Conference on Neural Networks, Atlanta, GA, USA,  pp 730–735 (2009)Google Scholar
  26. 26.
    Jia, X., Lou, Y., Li, R., Song, W.Y., Jiang, S.B.: GPU-based fast cone beam CT reconstruction from undersampled and noisy projection data via total variation. Med. Phys. 37(4), 1757–1760 (2010)CrossRefGoogle Scholar
  27. 27.
    Shams, R., Sadeghi, P., Kennedy, R., Hartley, R.: A survey of medical image registration on multicore and the GPU. IEEE Signal Process. Mag. 27(2), 50–60 (2010)CrossRefGoogle Scholar
  28. 28.
    Zanella, R., Zanghirati, G., Cavicchioli, R., Zanni, L., Boccacci, P., Bertero, M., Vicidomini, G.: Towards real-time image deconvolution: application to confocal and STED microscopy. Sci. Rep. 3 (2013)Google Scholar
  29. 29.
    Nasse, M.J., Woehl, J.C.: Realistic modeling of the illumination point spread function in confocal scanning optical microscopy. J. Opt. Soc. Am. A 27(2), 295–302 (2010)CrossRefGoogle Scholar
  30. 30.
    Bruce, M., Butte, M.: Real-time GPU-based 3D deconvolution. Opt. Express 21, 4766–4773 (2013)CrossRefGoogle Scholar
  31. 31.
    Mazanec, T., Hermánek, A., Kamenicky, J.: Blind image deconvolution algorithm on NVIDIA CUDA platform. In: Proceedings of IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems, Vienna, Austria, pp 125–126. IEEE (2010)Google Scholar
  32. 32.
    Pharr, M., Fernando, R.: GPU Gems 2: programming techniques for high-performance graphics and general-purpose computation (GPU Gems), Addison-Wesley Professional (2005)Google Scholar
  33. 33.
    Keys, R.G.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acoust. Speech Signal Process. 29, 1153–1160 (1981)MATHMathSciNetCrossRefGoogle Scholar
  34. 34.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Gr. 27(3), Article No. 73 (2008)Google Scholar
  35. 35.
  36. 36.
    Kim, K.J., Kwon, Y.H.: Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1127–1133 (2010)MathSciNetCrossRefGoogle Scholar
  37. 37.
    Wang, Z., Bovik, A.C.: Quality assessment: from error measurement to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  38. 38.
    Jung, C., Gu, A.: Curvature preserving image super-resolution with gradient-consistency-anisotropic-regularization prior. Sig. Process. Image Commun. 29(10), 1211–1222 (2014)CrossRefGoogle Scholar
  39. 39.
    Iovanovici, A., Visan, C., Marcu, M.: Performance and power consumption investigation for execution of integer operations on CPU and GPU processors for multimedia applications. In: Proceedings of IEEE Symposium on Intelligent Systems and Informatics, pp 285–289 (2009)Google Scholar
  40. 40.
    Govett, M., Middlecoff, J., Henderson, T.: Running the NIM next-generation weather model on GPUs. In: Proceedings of IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing,  Melbourne, Australia, pp 792–796 (2010)Google Scholar
  41. 41.
    Wahib, M., Maruyama, N.: Highly optimized full GPU-acceleration of non-hydrostatic weather model SCALE-LES. In: Proceedings of IEEE International Conference on Cluster Computing, Indianapolis, IN, USA,  pp 1–8 (2013)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Cheolkon Jung
    • 1
  • Peng Ke
    • 1
  • Zengzeng Sun
    • 1
  • Aiguo Gu
    • 1
  1. 1.School of Electronic EngineeringXidian UniversityXi’anChina

Personalised recommendations