ARTIFACT-FREE JPEG DECOMPRESSION WITH TOTAL GENERALIZED VARIATION

Kristian Bredies, Martin Holler

Abstract

We propose a new model for the improved reconstruction of JPEG (Joint Photographic Experts Group) images. Given a JPEG compressed image, our method first determines the set of possible source images and then specifically chooses one of these source images satisfying additional regularity properties. This is realized by employing the recently introduced Total Generalized Variation (TGV) as regularization term and solving a constrained minimization problem. In order to obtain an optimal solution numerically, we propose a primal-dual algorithm. We have developed a parallel implementation of this algorithm for the CPU and the GPU, using OpenMP and Nvidia’s Cuda, respectively. Finally, experiments have been performed, confirming a good visual reconstruction quality as well as the suitability for real-time application.

References

  1. Alter, F., Durand, S., and Froment, J. (2005). Adapted total variation for artifact free decompression of JPEG images. Journal of Mathematical Imaging and Vision, 23:199-211.
  2. Bredies, K. and Holler, M. (2011). A total-variationbased JPEG decompression model. Submitted for publication. Preprint available at http://math.unigraz.at/mobis/publications.html.
  3. Bredies, K., Kunisch, K., and Pock, T. (2010). Total generalized variation. SIAM Journal on Imaging Sciences, 3(3):492-526.
  4. Bredies, K. and Valkonen, T. (2011). Inverse problems with second-order total generalized variation constraints. In Proceedings of SampTA.
  5. Caselles, V., Chambolle, A., and Novaga, M. (2007). The discontinuity set of solutions of the TV denoising problem and some extensions. Multiscale Model. Simul., 6:879-894.
  6. Chambolle, A. and Pock, T. (2011). A first-order primaldual algorithm for convex problems with applications to imaging. Journal of Mathematical Imaging and Vision, 40:120-145.
  7. Dawgbyte77 (2008). http://www.flickr.com/photos/dawgbyte77/3052164481/.
  8. Frigo, M. and Johnson, S. G. (2005). The design and implementation of FFTW3. Proceedings of the IEEE, 93(2):216-231. Special issue on “Program Generation, Optimization, and Platform Adaptation”.
  9. Kartalov, T., Ivanovski, Z. A., Panovski, L., and Karam, L. J. (2007). An adaptive POCS algorithm for compression artifacts removal. In 9th International Symposium on Signal Processing and Its Applications, pages 1-4.
  10. Nikolova, M. (2000). Local strong homogeneity of a regularized estimator. SIAM J. Appl. Math., 61:633-658.
  11. Nosratinia, A. (2001). Enhancement of JPEG-compressed images by re-application of JPEG. The Journal of VLSI Signal Processing, 27:69-79.
  12. NVIDIA (2008). NVIDIA CUDA programming guide 2.0. NVIDIA Cooperation.
  13. OpenMP Architecture Review Board (2011). Openmp application program interface, version 3.1. http://www.openmp.org.
  14. Ring, W. (2000). Structural properties of solutions to total variation regularization problems. M2AN Math. Model. Numer. Anal., 34:799-810.
  15. Shen, M.-Y. and Kuo, C.-C. J. (1998). Review of postprocessing techniques for compression artifact removal. Journal of Visual Communication and Image Representation, 9(1):2-14.
  16. Singh, S., Kumar, V., and Verma, H. K. (2007). Reduction of blocking artifacts in JPEG compressed images. Digital Signal Processing, 17(1):225-243.
  17. Wallace, G. K. (1991). The JPEG still picture compression standard. Commun. ACM, 34(4):30-44.
  18. Weerasinghe, C., Liew, A. W.-C., and Yan, H. (2002). Artifact reduction in compressed images based on region homogeneity constraints using the projection onto convex sets algorithm. IEEE Transactions on Circuits and Systems for Video Technology, 12(10):891-897.
  19. Zhong, S. (1997). Image coding with optimal reconstruction. In International Conference on Image Processing, volume 1, pages 161-164.
  20. Zou, J. J. and Yan, H. (2005). A deblocking method for BDCT compressed images based on adaptive projections. IEEE Transactions on Circuits and Systems for Video Technology, 15(3):430-435.
Download


Paper Citation


in Harvard Style

Bredies K. and Holler M. (2012). ARTIFACT-FREE JPEG DECOMPRESSION WITH TOTAL GENERALIZED VARIATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 12-21. DOI: 10.5220/0003824500120021


in Bibtex Style

@conference{visapp12,
author={Kristian Bredies and Martin Holler},
title={ARTIFACT-FREE JPEG DECOMPRESSION WITH TOTAL GENERALIZED VARIATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={12-21},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003824500120021},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - ARTIFACT-FREE JPEG DECOMPRESSION WITH TOTAL GENERALIZED VARIATION
SN - 978-989-8565-03-7
AU - Bredies K.
AU - Holler M.
PY - 2012
SP - 12
EP - 21
DO - 10.5220/0003824500120021