Semi-discrete Optimal Transport in Patch Space for Enriching Gaussian Textures

  • Bruno Galerne
  • Arthur Leclaire
  • Julien Rabin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10589)


A bilevel texture model is proposed, based on a local transform of a Gaussian random field. The core of this method relies on the optimal transport of a continuous Gaussian distribution towards the discrete exemplar patch distribution. The synthesis then simply consists in a fast post-processing of a Gaussian texture sample, boiling down to an improved nearest-neighbor patch matching, while offering theoretical guarantees on statistical compliancy.


Optimal transport Texture synthesis Patch distribution 



This work has been partially funded by Project Texto (Projet Jeunes Chercheurs du GdR Isis).


  1. 1.
    Aurenhammer, F., Hoffmann, F., Aronov, B.: Minkowski-type theorems and least-squares clustering. Algorithmica 20(1), 61–76 (1998)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proceedings of the ICCV 1999, p. 1033 (1999)Google Scholar
  3. 3.
    Efros, A., Freeman, W.: Image quilting for texture synthesis and transfer. In: ACM TOG, pp. 341–346, August 2001Google Scholar
  4. 4.
    Galerne, B., Gousseau, Y., Morel, J.M.: Random phase textures: theory and synthesis. IEEE Trans. Image Process. 20(1), 257–267 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Galerne, B., Leclaire, A.: Texture inpainting using efficient Gaussian conditional simulation. SIIMS 10(3), 1446–1474 (2017)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Galerne, B., Leclaire, A., Moisan, L.: A texton for fast and flexible Gaussian texture synthesis. In: Proceedings of the EUSIPCO, pp. 1686–1690 (2014)Google Scholar
  7. 7.
    Galerne, B., Leclaire, A., Moisan, L.: Texton noise. Comput. Graph. Forum (2017). doi: 10.1111/cgf.13073
  8. 8.
    Genevay, A., Cuturi, M., Peyré, G., Bach, F.: Stochastic optimization for large-scale optimal transport. In: Proceedings of the NIPS, pp. 3432–3440 (2016)Google Scholar
  9. 9.
    Gutierrez, J., Rabin, J., Galerne, B., Hurtut, T.: Optimal patch assignment for statistically constrained texture synthesis. In: Lauze, F., Dong, Y., Dahl, A.B. (eds.) SSVM 2017. LNCS, vol. 10302, pp. 172–183. Springer, Cham (2017). doi: 10.1007/978-3-319-58771-4_14 CrossRefGoogle Scholar
  10. 10.
    Kitagawa, J., Mérigot, Q., Thibert, B.: A Newton algorithm for semi-discrete optimal transport. J. Eur. Math Soc. (2017)Google Scholar
  11. 11.
    Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: Texture optimization for example-based synthesis. ACM TOG 24(3), 795–802 (2005)CrossRefGoogle Scholar
  12. 12.
    Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: image and video synthesis using graph cuts. ACM TOG 22(3), 277–286 (2003)CrossRefGoogle Scholar
  13. 13.
    Lefebvre, S., Hoppe, H.: Parallel controllable texture synthesis. ACM TOG 24(3), 777–786 (2005)CrossRefGoogle Scholar
  14. 14.
    Levina, E., Bickel, P.: Texture synthesis and nonparametric resampling of random fields. Ann. Stat. 34(4), 1751–1773 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  15. 15.
    Lévy, B.: A numerical algorithm for L2 semi-discrete optimal transport in 3D. ESAIM: M2AN 49(6), 1693–1715 (2015)CrossRefzbMATHGoogle Scholar
  16. 16.
    Liang, L., Liu, C., Xu, Y.Q., Guo, B., Shum, H.Y.: Real-time texture synthesis by patch-based sampling. ACM TOG 20(3), 127–150 (2001)CrossRefGoogle Scholar
  17. 17.
    Mérigot, Q.: A multiscale approach to optimal transport. Comput. Graph. Forum 30(5), 1583–1592 (2011)CrossRefGoogle Scholar
  18. 18.
    Moulines, E., Bach, F.: Non-asymptotic analysis of stochastic approximation algorithms for machine learning. In: Proceedings of the NIPS, pp. 451–459 (2011)Google Scholar
  19. 19.
    Raad, L., Desolneux, A., Morel, J.: A conditional multiscale locally Gaussian texture synthesis algorithm. J. Math. Imaging Vis. 56(2), 260–279 (2016)CrossRefzbMATHMathSciNetGoogle Scholar
  20. 20.
    Rabin, J., Peyré, G., Delon, J., Bernot, M.: Wasserstein barycenter and its application to texture mixing. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds.) SSVM 2011. LNCS, vol. 6667, pp. 435–446. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-24785-9_37 CrossRefGoogle Scholar
  21. 21.
    Tartavel, G., Peyré, G., Gousseau, Y.: Wasserstein loss for image synthesis and restoration. SIAM J. Imaging Sci. 9(4), 1726–1755 (2016)CrossRefzbMATHMathSciNetGoogle Scholar
  22. 22.
    Villani, C.: Topics in Optimal Transportation. American Mathematical Society, Providence (2003)CrossRefzbMATHGoogle Scholar
  23. 23.
    Wei, L.Y., Lefebvre, S., Kwatra, V., Turk, G.: State of the art in example-based texture synthesis. In: Eurographics, State of the Art Reports, pp. 93–117 (2009)Google Scholar
  24. 24.
    Wei, L.Y., Levoy, M.: Fast texture synthesis using tree-structured vector quantization. In: Proceedings of the SIGGRAPH 2000, pp. 479–488 (2000)Google Scholar
  25. 25.
    Xia, G., Ferradans, S., Peyré, G., Aujol, J.: Synthesizing and mixing stationary gaussian texture models. SIAM J. Imaging Sci. 7(1), 476–508 (2014)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Laboratoire MAP5Université Paris Descartes and CNRS, Sorbonne Paris CitéParisFrance
  2. 2.CMLA, ENS Cachan, CNRSUniversité Paris-SaclayCachanFrance
  3. 3.Normandie Univ, ENSICAEN, CNRS, GREYCCaenFrance

Personalised recommendations