Iterative Gradient-Driven Patch-Based Inpainting

  • Sarawut Tae-o-sot
  • Akinori Nishihara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7088)

Abstract

A novel exemplar-based image inpainting is proposed in this paper. This method is based on iterative approach which provides better result than greedy one. The problem of inconsistent results caused by raster scanning on target patch selection in iterative approach is focused in this paper. The proposed gradient-driven ordering is used to select target patch instead of traditionally predefined ordering. Due to the information-driven nature, this new approach is image’s rotation invariant which means the same result is provided by different rotation of the same damaged image. Moreover, a random search approach is redesigned to be more reasonable and suitable for our novel gradient-driven ordering. The proposed method provides the best inpainting result among several well-known exemplar-based inpainting techniques including both greedy and iterative approach.

Keywords

image completion image inpainting exemplar-based patchmatch 

References

  1. 1.
    Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics (Proc. SIGGRAPH) 28(3) (August 2009)Google Scholar
  2. 2.
    Bertalmío, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: SIGGRAPH, pp. 417–424 (2000)Google Scholar
  3. 3.
    Bertalmío, M., Vese, L.A., Sapiro, G., Osher, S.: Simultaneous structure and texture image inpainting. IEEE Transactions on Image Processing 12(8), 882–889 (2003)CrossRefGoogle Scholar
  4. 4.
    Chan, T.F., Shen, J.: Local inpainting models and tv inpainting. SIAM Journal on Applied Mathematics 62(3), 1019–1043 (2001)MathSciNetGoogle Scholar
  5. 5.
    Chan, T.F., Shen, J.: Non-texture inpainting by curvature-driven diffusions (cdd). J. Visual Comm. Image Rep. 12, 436–449 (2001)CrossRefGoogle Scholar
  6. 6.
    Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing 13(9), 1200–1212 (2004)CrossRefGoogle Scholar
  7. 7.
    Efros, A., Leung, T.: Texture synthesis by non-parametric sampling. In: International Conference on Computer Vision, pp. 1033–1038 (1999)Google Scholar
  8. 8.
    Kanizsa, G.: Organization in Vision. Holt, Rinehart Winston (1979)Google Scholar
  9. 9.
    Komodakis, N., Tziritas, G.: Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Transactions on Image Processing 16(11), 2649–2661 (2007)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kwok, T.H., Sheung, H., Wang, C.C.: Fast query for exemplar-based image completion. IEEE Transactions on Image Processing 19, 3106–3115 (2010)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Lee, S.Y., Heu, J.H., Kim, C.S., Lee, S.U.: Object removal and inpainting in multi-view video sequences. International Journal of Innovative Computing, Information and Control 6(3(B)) (March 2010)Google Scholar
  12. 12.
    Simakov, D., Caspi, Y., Shechtman, E., Irani, M.: Summarizing visual data using bidirectional similarity. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1 –8 (June 2008)Google Scholar
  13. 13.
    Tae-o-sot, S., Nishihara, A.: Exemplar-based image inpainting with patch shifting scheme. In: 17th International Conference on Digital Signal Processing (2011)Google Scholar
  14. 14.
    Wexler, Y., Shechtman, E., Irani, M.: Space-time completion of video. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 463–476 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sarawut Tae-o-sot
    • 1
  • Akinori Nishihara
    • 2
  1. 1.The Department of Communications and Integrated SystemsTokyo Institute of TechnologyTokyoJapan
  2. 2.The Center for Research and Development of Educational TechnologyTokyo Institute of TechnologyTokyoJapan

Personalised recommendations