Skip to main content
SpringerLink
Log in

Artifact-Free Variational MPEG Decompression

  • Conference paper
  • First Online:
Scale Space and Variational Methods in Computer Vision (SSVM 2015)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9087))

  • 2238 Accesses

Abstract

We propose a variational method for artifact-free video decompression that is capable of processing any MPEG-2 encoded movie. The method extracts, from a given MPEG-2 file, a set of admissible image sequences and minimizes an artifact-penalizing spatio-temporal regularization functional over this set, giving an optimal decompressed image sequence. For regularization, we use the infimal convolution of spatio-temporal Total Generalized Variation functionals (ICTGV). Numerical experiments on MPEG encoded files show that our approach significantly increases image quality compared to standard decompression.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aubert, G., Kornprobst, P.: Mathematical Problems in Image Processing. Springer (2006)

    Google Scholar 

  2. Bredies, K., Holler, M.: A total variation-based JPEG decompression model. SIAM J. Imag. Sci. 5(1), 366–393 (2012)

    Article  MATH  MathSciNet  Google Scholar 

  3. Bredies, K., Holler, M.: Artifact-free decompression and zooming of JPEG compressed images with total generalized variation. In: Csurka, G., Kraus, M., Laramee, R.S., Richard, P., Braz, J. (eds.) VISIGRAPP 2012. CCIS, vol. 359, pp. 242–258. Springer, Heidelberg (2013)

    Google Scholar 

  4. Bredies, K., Holler, M.: Regularization of linear inverse problems with total generalized variation. J. Inverse Ill-Posed Probl. (2014). doi:10.1515/jip-2013-0068

  5. Bredies, K., Kunisch, K., Pock, T.: Total generalized variation. SIAM J. Imag. Sci. 3(3), 492–526 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  6. Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vision 40, 120–145 (2011)

    Article  MATH  MathSciNet  Google Scholar 

  7. Ekeland, I., Témam, R.: Convex Analysis and Variational Problems. SIAM (1999)

    Google Scholar 

  8. Holler, M., Kunisch, K.: On infimal convolution of TV-type functionals and applications to video and image reconstruction. SIAM J. Imag. Sci. 7(4), 2258–2300 (2014)

    Article  MATH  MathSciNet  Google Scholar 

  9. Kocovski, B., Kartalov, T., Ivanovski, Z., Panovski, L.: An adaptive deblocking algorithm for low bit-rate video. In: 3rd International Symposium on ISCCSP 2008, pp. 888–893, March 2008

    Google Scholar 

  10. Webpage of Martin Holler. http://www.uni-graz.at/~hollerm/research.html

  11. Middlebury optical flow dataset. http://vision.middlebury.edu/flow/

  12. Schaeffer, H., Yang, Y., Osher, S.: Space-time regularization for video decompression (2014). Preprint

    Google Scholar 

  13. Schrijver, A.: Theory of Linear and Integer Programming. John Wiley & Sons (1986)

    Google Scholar 

  14. Arizona State University. Video trace library. http://trace.eas.asu.edu/

  15. Zhong, S.: Image coding with optimal reconstruction. International Conference on Image Processing 1, 161–164 (1997)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute for Mathematics and Scientific Computing, University of Graz, Graz, Austria

    Kristian Bredies & Martin Holler

Authors
  1. Kristian Bredies
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Martin Holler
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Martin Holler .

Editor information

Editors and Affiliations

  1. University of Bordeaux, Talence, France

    Jean-François Aujol

  2. ENS Cachan, Cachan, France

    Mila Nikolova

  3. University of Bordeaux, Talence, France

    Nicolas Papadakis

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Bredies, K., Holler, M. (2015). Artifact-Free Variational MPEG Decompression. In: Aujol, JF., Nikolova, M., Papadakis, N. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2015. Lecture Notes in Computer Science(), vol 9087. Springer, Cham. https://doi.org/10.1007/978-3-319-18461-6_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-18461-6_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-18460-9

  • Online ISBN: 978-3-319-18461-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation