COMBINING TEXTURE SYNTHESIS AND DIFFUSION FOR IMAGE INPAINTING

Aurélie Bugeau, Marcelo Bertalmío

Abstract

Image inpainting or image completion consists in filling in the missing data of an image in a visually plausible way. Many works on this subject have been proposed these recent years. They can mainly be decomposed into two groups: geometric methods and texture synthesis methods. Texture synthesis methods work best with images containing only textures while geometric approaches are limited to smooth images containing strong edges. In this paper, we first present an extended state of the art. Then a new algorithm dedicated to both types of images is introduced. The basic idea is to decompose the original image into a structure and a texture image. Each of them is then filled in with some extensions of one of the best methods from the literature. A comparison with some existing methods on different natural images shows the strength of the proposed approach.

References

  1. Ballester, C., Bertalmío, M., Caselles, V., Sapiro, G., and Verdera, J. (2001). Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans. on Im. Processing, 10(8):1200-1211.
  2. Bertalmío, M. (2006). Strong-continuation, contrastinvariant inpainting with a third-order optimal pde. IEEE Trans. on Im. Processing, 15(7):1934-1938.
  3. Bertalmio, M., Sapiro, G., Caselles, V., and Ballester, C. (2000). Image inpainting. In SIGGRAPH: ACM Special Interest Group on Comp. Graphics and Interactive Techniques.
  4. Bertalmio, M., Vese, L., Sapiro, G., and Osher, S. (2003). Simultaneous structure and texture image inpainting. IEEE Trans. on Im. Processing, 12(8):882-889.
  5. Bornemann, F. and März, T. (2007). Fast image inpainting based on coherence transport. Journal of Mathematical Imaging and Vis., 28(3):259-278.
  6. Chan, T., Kang, S., and Shen, J. (2002). Euler's elastica and curvature based inpaintings. Journal of Appl. Math., 63:564-592.
  7. Chan, T., Osher, S., and Shen, J. (2001). The digital tv filter and nonlinear denoising. IEEE Trans. on Im. Processing, 10(2):231-241.
  8. Chan, T. and Shen, J. (2001). Nontexture inpainting by curvature-driven diffusions. Journal of Visual Communication and Im. Representation, 12(4):436-449.
  9. Criminisi, A., Pérez, P., and Toyama, K. (2004). Region filling and object removal by exemplar-based inpainting. IEEE Trans. on Im. Processing, 13(9):1200-1212.
  10. Efros, A. and Leung, T. (1999). Texture synthesis by nonparametric sampling. In In Proc. of the Int. Conf. on Comp. Vis.
  11. Harrison, P. (2001). A non-hierarchical procedure for resynthesis of complex textures. In WSCG Conf. Proc.
  12. Masnou, S. (2002). Disocclusion: a variational approach using level lines. IEEE Trans. on Im. Processing, 11(2):68-76.
  13. Masnou, S. and Morel, J. (1998). Level-lines based disocclusion. In Proceedings of 5th IEEE Intl Conf. on Image Process., Chicago, volume 3, pages 259-263.
  14. Meyer, Y. (2001). Oscillating patterns in image processing and nonlinear evolution equations. American Mathematical Society, Providence, RI.
  15. Mumford, D. (1994). Algebraic Geometry and its Applications, chapter Elastica and Computer Vision, pages 491-506. Chandrajit Bajaj, New York, SpringerVerlag.
  16. Sun, J., Yuan, L., Jia, J., and Shum, H. (2005). Image completion with structure propagation. In SIGGRAPH: ACM Special Interest Group on Comp. Graphics and Interactive Techniques.
  17. Telea, A. (2004). An image inpainting technique based on the fast marching method. Journal of graphics tools, 9(1):23-34.
  18. Tschumperlé, D. (2006). Fast anisotropic smoothing of multi-valued images using curvature-preserving pde's. Int. Journal of Comp. Vis., 68(1):65-82.
  19. Tschumperle, D. and Deriche, R. (2005). Vector-valued image regularization with pdes: a common framework for different applications. IEEE Trans. on Pat. Analysis and Machine Intelligence, 27(4):506-517.
  20. Vese, L. and Osher, S. (2003). Modeling textures with total variation minimization and oscillating patterns in image processing. Journal scientific Computing, 19(1- 3):553-572.
  21. Weickert, J. (1998). Anisotropic diffusion in image processing. Teubner Verlag, Stuttgart.
Download


Paper Citation


in Harvard Style

Bugeau A. and Bertalmío M. (2009). COMBINING TEXTURE SYNTHESIS AND DIFFUSION FOR IMAGE INPAINTING . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 26-33. DOI: 10.5220/0001773900260033


in Bibtex Style

@conference{visapp09,
author={Aurélie Bugeau and Marcelo Bertalmío},
title={COMBINING TEXTURE SYNTHESIS AND DIFFUSION FOR IMAGE INPAINTING},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={26-33},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001773900260033},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - COMBINING TEXTURE SYNTHESIS AND DIFFUSION FOR IMAGE INPAINTING
SN - 978-989-8111-69-2
AU - Bugeau A.
AU - Bertalmío M.
PY - 2009
SP - 26
EP - 33
DO - 10.5220/0001773900260033