Advertisement

Tensor-Directed Spatial Patch Blending for Pattern-Based Inpainting Methods

  • Maxime DaisyEmail author
  • Pierre Buyssens
  • David Tschumperlé
  • Olivier Lézoray
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9256)

Abstract

Despite the tremendous advances made in recent years, in the field of patch-based image inpainting algorithms, it is not uncommon to still get visible artefacts in the parts of the images that have been resynthetized using this kind of methods. Mostly, these artifacts take the form of discontinuities between synthetized patches which have been copied/pasted in nearby regions, but from very different source locations. In this paper, we propose a generic patch blending formalism which aims at strongly reducing this kind of artifacts. To achieve this, we define a tensor-directed anisotropic blending algorithm for neighboring patches, inspired somehow from what is done by anisotropic smoothing PDE’s for the classical image regularization problem. Our method has the advantage of blending/removing incoherent patch data while preserving the significant structures and textures as much as possible. It is really fast to compute, and adaptable to most patch-based inpainting algorithms in order to visually enhance the quality of the synthetized results.

Keywords

Patch Blending Tensor-directed Geometry-aware Anisotropy 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arias, P., Facciolo, G., Caselles, V., Sapiro, G.: A variational framework for exemplar-based image inpainting. International Journal of Computer Vision 93(3), 319–347 (2011). http://dx.doi.org/10.1007/s11263-010-0418-7 MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Ashikhmin, M.: Synthesizing natural textures. In: Proceedings of the 2001 Symposium on Interactive 3D Graphics, pp. 217–226. ACM (2001)Google Scholar
  3. 3.
    Ballester, C., Bertalmio, M., Caselles, V., Sapiro, G., Verdera, J.: Filling-in by joint interpolation of vector fields and gray levels. IEEE Transactions on Image Processing 10(8), 1200–1211 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417–424 (2000)Google Scholar
  5. 5.
    Bornard, R., Lecan, E., Laborelli, L., Chenot, J.H.: Missing data correction in still images and image sequences. In: Proceedings of the Tenth ACM International Conference on Multimedia, pp. 355–361 (2002)Google Scholar
  6. 6.
    Bornemann, F., März, T.: Fast image inpainting based on coherence transport. Journal of Mathematical Imaging and Vision 28(3), 259–278 (2007)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Bugeau, A., Bertalmio, M., et al.: Combining texture synthesis and diffusion for image inpainting. In: Combining Texture Synthesis and Diffusion for Image Inpainting, pp. 26–33 (2009)Google Scholar
  8. 8.
    Cao, F., Gousseau, Y., Masnou, S., Pérez, P.: Geometrically guided exemplar-based inpainting. SIAM Journal on Imaging Sciences 4(4), 1143–1179 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    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
  10. 10.
    Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: Computer Vision and Pattern Recognition, vol. 2, pp. II-721. IEEE (2003)Google Scholar
  11. 11.
    Daisy, M., Buyssens, P., Tschumperlé, D., Lézoray, O.: A smarter exemplar-based inpainting algorithm using local and global heuristics for more geometry coherence. In: Internation Conference on Image Processing, Paris, France (2014)Google Scholar
  12. 12.
    Daisy, M., Tschumperlé, D., Lézoray, O.: A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting. In: SIGGRAPH Asia 2013 Technical Briefs (2013)Google Scholar
  13. 13.
    Daisy, M., Tschumperlé, D., Lézoray, O.: Spatial patch blending for artefact reduction in pattern-based inpainting techniques. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds.) CAIP 2013, Part II. LNCS, vol. 8048, pp. 523–530. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  14. 14.
    Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: International Conference on Computer Vision, vol. 2, pp. 1033–1038. IEEE (1999)Google Scholar
  15. 15.
    Guillemot, C., Le Meur, O.: Image inpainting: Overview and recent advances. Signal Processing Magazine, IEEE 31(1), 127–144 (2014)CrossRefGoogle Scholar
  16. 16.
    Jia, J., Tang, C.K.: Inference of segmented color and texture description by tensor voting. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(6), 771–786 (2004)CrossRefGoogle Scholar
  17. 17.
    Le Meur, O., Ebdelli, M., Guillemot, C.: Hierarchical super-resolution-based inpainting. IEEE Transactions on Image Processing 22(10), 3779–3790 (2013)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Le Meur, O., Gautier, J., Guillemot, C.: Examplar-based inpainting based on local geometry. In: International Conference on Image Processing, Brussel, Belgium, pp. 3401–3404 (2011). http://hal.inria.fr/inria-00628074
  19. 19.
    Masnou, S., Morel, J.M.: Level lines based disocclusion. In: International Conference on Image Processing (3), pp. 259–263 (1998)Google Scholar
  20. 20.
    Pérez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Transactions on Graphics 22(3), 313–318 (2003)CrossRefGoogle Scholar
  21. 21.
    Tschumperlé, D., Deriche, R.: Vector-valued image regularization with pdes: A common framework for different applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(4), 506–517 (2005)CrossRefGoogle Scholar
  22. 22.
    Wexler, Y., Shechtman, E., Irani, M.: Space-time completion of video. IEEE Transaction on Pattern Analysis and Machince Intelligence 29(3), 463–476 (2007)CrossRefGoogle Scholar
  23. 23.
    Di Zenzo, S.: A note on the gradient of a multi-image. Computer Vision, Graphics, and Image Processing 33(1), 116–125 (1986). http://www.sciencedirect.com/science/article/pii/0734189X86902239 CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Maxime Daisy
    • 1
    Email author
  • Pierre Buyssens
    • 1
  • David Tschumperlé
    • 1
  • Olivier Lézoray
    • 1
  1. 1.GREYC CNRS UMR6072CaenFrance

Personalised recommendations