Archive Film Restoration Based on Spatiotemporal Random Walks

  • Xiaosong Wang
  • Majid Mirmehdi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


We propose a novel restoration method for defects and missing regions in video sequences, particularly in application to archive film restoration. Our statistical framework is based on random walks to examine the spatiotemporal path of a degraded pixel, and uses texture features in addition to intensity and motion information traditionally used in previous restoration works. The degraded pixels within a frame are restored in a multiscale framework by updating their features (intensity, motion and texture) at each level with reference to the attributes of normal pixels and other defective pixels in the previous scale as long as they fall within the defective pixel’s random walk-based spatiotemporal neighbourhood. The proposed algorithm is compared against two state-of-the-art methods to demonstrate improved accuracy in restoring synthetic and real degraded image sequences.


Random Walk Mean Square Error Motion Vector Local Binary Pattern Texture Synthesis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proc. SIGGRAPH, pp. 417–424 (2000)Google Scholar
  2. 2.
    Bornard, R., Lecan, E., Laborelli, L., Chenot, J.H.: Missing data correction in still images and image sequences. In: Proc. MULTIMEDIA, pp. 355–361 (2002)Google Scholar
  3. 3.
    Chan, T.F., Kang, S.H., Shen, J.: Euler’s elastica and curvature driven diffusions. SIAM J. App. Math. 2, 564–592 (2002)MathSciNetGoogle Scholar
  4. 4.
    Chan, T.F., Shen, J.: Image Processing and Analysis. SIAM, Philadelphia (2005)zbMATHGoogle Scholar
  5. 5.
    Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. IP 13(9), 1–13 (2004)Google Scholar
  6. 6.
    Efros, A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Proc. SIGGRAPH, pp. 341–346 (2001)Google Scholar
  7. 7.
    Efros, A., Leung, T.: Texture synthesis by non-parametric sampling. In: Proc. ICCV, vol. 2, pp. 1033–1038 (1999)Google Scholar
  8. 8.
    Esedoglu, S., Shen, J.: Digital inpainting based on the mumford-shah-euler image model. Euro. J. App. Math. 13(4), 353–370 (2002)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Estrada, F., Fleet, D., Jepson, A.: Stochastic image denoising. In: Proc. BMVC (2009)Google Scholar
  10. 10.
    Gangal, A., Dizdaroglu, B.: Automatic restoration of old motion picture films using spatiotemporal exemplar-based inpainting. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2006. LNCS, vol. 4179, pp. 55–66. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Grady, L.: Random walk for image segmentation. IEEE Trans. PAMI 28(11), 1768–1783 (2006)Google Scholar
  12. 12.
    Hamid, M.S., Harvey, N., Marshall, S.: Genetic algorithm optimization of multidimensional grayscale soft morphological filters with applications in film archive restoration. IEEE Trans. CSVT 13(5), 406–416 (2003)Google Scholar
  13. 13.
    Hardie, R., Boncelet, C.: Lum filters: a class of rank-order-based filters for smoothing and sharpening. IEEE Trans. SP 41(3), 1061–1076 (1993)zbMATHCrossRefGoogle Scholar
  14. 14.
    Heeger, D.J., Bergen, J.R.: Pyramid-based texture analysis/synthesis. In: Proc. SIGGRAPH, pp. 229–238 (1995)Google Scholar
  15. 15.
    Kokaram, A.: On missing data treatment for degraded video and film archives: a survey and a new bayesian approach. IEEE Trans. IP 13(3), 397–415 (2004)Google Scholar
  16. 16.
    Kokaram, A., Godsill, S.: Mcmc for joint noise reduction and missing data treatment in degraded video. IEEE Trans. SP 50(2), 189–205 (2002)CrossRefGoogle Scholar
  17. 17.
    Kokaram, A., Morris, R., Fitzgerald, W., Rayner, P.: Interpolation of missing data in image sequences. IEEE Trans. IP 4(11), 1509–1519 (1995)Google Scholar
  18. 18.
    Masnou, S., Morel, J.M.: Level lines based disocclusion. In: Proc. ICIP, vol. 3, pp. 259–263 (1998)Google Scholar
  19. 19.
    Morris, R.: Image Sequence Restoration using Gibbs Distributions. Ph.D. thesis, Cambridge University (1995)Google Scholar
  20. 20.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE trans. PAMI 24(7), 971–987 (2002)Google Scholar
  21. 21.
    Patwardhan, K., Sapiro, G., Bertalmio, M.: Video inpainting of occluding and occluded objects. In: Proc. ICIP, vol. 2, pp. II: 69–72 (2005)Google Scholar
  22. 22.
    Ren, J., Vlachos, T.: Efficient detection of temporally impulsive dirt impairments in archived films. Signal Processing 87(3), 541–551 (2007)zbMATHCrossRefGoogle Scholar
  23. 23.
    Roosmalen, P.M.B.V.: Restoration of Archived Film and Video. Ph.D. thesis, Delft University of Technology (1999)Google Scholar
  24. 24.
    Wang, X., Mirmehdi, M.: HMM based archive film defect detection with spatial and temporal constraints. In: Proc. BMVC (2009)Google Scholar
  25. 25.
    Wexler, Y., Shechtman, E., Irani, M.: Space-time video completion. In: Proc. CVPR, vol. 1, pp. 120–127 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xiaosong Wang
    • 1
  • Majid Mirmehdi
    • 1
  1. 1.Computer Vision Group, Department of Computer ScienceUniversity of BristolBristolUK

Personalised recommendations