Wasserstein Generative Models for Patch-Based Texture Synthesis

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12679)


This work addresses texture synthesis by relying on the local representation of images through their patch distributions. The main contribution is a framework that imposes the patch distributions at several scales using optimal transport. This leads to two formulations. First, a pixel-based optimization method is proposed, based on discrete optimal transport. We show that it generalizes a well-known texture optimization method that uses iterated patch nearest-neighbor projections, while avoiding some of its shortcomings. Second, in a semi-discrete setting, we exploit differential properties of Wasserstein distances to learn a fully convolutional network for texture generation. Once estimated, this network produces realistic and arbitrarily large texture samples in real time. By directly dealing with the patch distribution of synthesized images, we also overcome limitations of state-of-the-art techniques, such as patch aggregation issues that usually lead to low frequency artifacts (e.g. blurring) in traditional patch-based approaches, or statistical inconsistencies (e.g. color or patterns) in machine learning approaches.


  1. 1.
    Bergmann, U., Jetchev, N., Vollgraf, R.: Learning texture manifolds with the periodic spatial gan. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 469–477. (2017)Google Scholar
  2. 2.
    Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 60–65. IEEE (2005)Google Scholar
  3. 3.
    Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: IEEE International Conference on Computer Vision, p. 1033 (1999)Google Scholar
  4. 4.
    Galerne, B., Leclaire, A., Rabin, J.: A texture synthesis model based on semi-discrete optimal transport in patch space. SIAM J. Imaging Sci. 11(4), 2456–2493 (2018)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Gatys, L., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: NIPS, pp. 262–270 (2015)Google Scholar
  6. 6.
    Genevay, A., Cuturi, M., Peyré, G., Bach, F.: Stochastic optimization for large-scale optimal transport. In: Advances in Neural Information Processing Systems, pp. 3440–3448 (2016)Google Scholar
  7. 7.
    Gutierrez, J., Galerne, B., Rabin, J., Hurtut, T.: Optimal patch assignment for statistically constrained texture synthesis. In: Scale-Space and Variational Methods in Computer Vision (2017)Google Scholar
  8. 8.
    Houdard, A., Bouveyron, C., Delon, J.: High-dimensional mixture models for unsupervised image denoising (HDMI). SIAM J. Imaging Sci. 11(4), 2815–2846 (2018)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)Google Scholar
  10. 10.
    Kaspar, A., Neubert, B., Lischinski, D., Pauly, M., Kopf, J.: Self tuning texture optimization. Comput. Graph. Forum 34, 349–359 (2015)CrossRefGoogle Scholar
  11. 11.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)Google Scholar
  12. 12.
    Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: Texture optimization for example-based synthesis. In: ACM SIGGRAPH 2005 Papers, pp. 795–802 (2005)Google Scholar
  13. 13.
    Lebrun, M., Buades, A., Morel, J.M.: A nonlocal bayesian image denoising algorithm. SIAM J. Imaging Sci. 6(3), 1665–1688 (2013)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Leclaire, A., Rabin, J.: A fast multi-layer approximation to semi-discrete optimal transport. In: Lellmann, J., Burger, M., Modersitzki, J. (eds.) SSVM 2019. LNCS, vol. 11603, pp. 341–353. Springer, Cham (2019). Scholar
  15. 15.
    Liu, G., Gousseau, Y., Xia, G.: Texture synthesis through convolutional neural networks and spectrum constraints. In: International Conference on Pattern Recognition (ICPR), pp. 3234–3239. IEEE (2016)Google Scholar
  16. 16.
    Santambrogio, F.: Optimal transport for applied mathematicians. Progr. Nonlinear Differ. Equ. Appl. 87 (2015)Google Scholar
  17. 17.
    Shaham, T.R., Dekel, T., Michaeli, T.: Singan: learning a generative model from a single natural image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4570–4580 (2019)Google Scholar
  18. 18.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  19. 19.
    Ulyanov, D., Lebedev, V., Vedaldi, A., Lempitsky, V.: Texture networks: feed-forward synthesis of textures and stylized images. In: Proceedings of the International Conference on Machine Learning, vol. 48, pp. 1349–1357 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Univ. Bordeaux, Bordeaux INP, CNRS, IMBTalenceFrance
  2. 2.Normandie Univ., UniCaen, ENSICAEN, CNRS, GREYC, UMR 607CaenFrance

Personalised recommendations