Abstract
The optimal transport (OT) framework has been largely used in inverse imaging and computer vision problems, as an interesting way to incorporate statistical constraints or priors. In recent years, OT has also been used in machine learning, mostly as a metric to compare probability distributions. This work addresses the semi-discrete OT problem where a continuous source distribution is matched to a discrete target distribution. We introduce a fast stochastic algorithm to approximate such a semi-discrete OT problem using a hierarchical multi-layer transport plan. This method allows for tractable computation in high-dimensional case and for large point-clouds, both during training and synthesis time. Experiments demonstrate its numerical advantage over multi-scale (or multi-level) methods. Applications to fast exemplar-based texture synthesis based on patch matching with two layers, also show stunning improvements over previous single layer approaches. This shallow model achieves comparable results with state-of-the-art deep learning methods, while being very compact, faster to train, and using a single image during training instead of a large dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aurenhammer, F., Hoffmann, F., Aronov, B.: Minkowski-type theorems and least-squares clustering. Algorithmica 20(1), 61–76 (1998)
Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. TOG 28(3), 24 (2009)
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)
Genevay, A., Cuturi, M., Peyré, G., Bach, F.: Stochastic optimization for large-scale optimal transport. In: Proceedings of NIPS, pp. 3432–3440 (2016)
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). https://doi.org/10.1007/978-3-319-58771-4_14
Kitagawa, J.: An iterative scheme for solving the optimal transportation problem. Calc. Var. Partial Differ. Equ. 51(1–2), 243–263 (2014)
Kitagawa, J., Mérigot, Q., Thibert, B.: A Newton algorithm for semi-discrete optimal transport. J. Eur. Math Soc. (2017)
Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: Texture optimization for example-based synthesis. ACM TOG 24(3), 795–802 (2005)
Lévy, B.: A numerical algorithm for L2 semi-discrete optimal transport in 3D. ESAIM: M2AN 49(6), 1693–1715 (2015)
Liu, J., Yin, W., Li, W., Chow, Y.T.: Multilevel optimal transport: a fast approximation of wasserstein-1 distances. arXiv preprint arXiv:1810.00118 (2018)
Mérigot, Q.: A multiscale approach to optimal transport. Comput. Graph. Forum 30(5), 1583–1592 (2011)
Oberman, A.M., Ruan, Y.: An efficient linear programming method for optimal transportation. arXiv preprint arXiv:1509.03668 (2015)
Rabin, J., Peyré, G.: Wasserstein regularization of imaging problems. In: 2011 IEEE International Conference on Image Processing, ICIP 2011 (2011)
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). https://doi.org/10.1007/978-3-642-24785-9_37
Rubner, Y., Tomasi, C., Guibas, L.J.: A metric for distributions with applications to image databases. In: Sixth International Conference on Computer Vision, pp. 59–66. IEEE (1998)
Santambrogio, F.: Optimal Transport for Applied Mathematicians. Birkäuser (2015)
Schmitzer, B.: A sparse multiscale algorithm for dense optimal transport. J. Math. Imaging Vis. 56(2), 238–259 (2016)
Solomon, J., et al.: Convolutional wasserstein distances: efficient optimal transportation on geometric domains. ACM Trans. Graph. (TOG) 34(4), 66 (2015)
Tartavel, G., Gousseau, Y., Peyré, G.: Variational texture synthesis with sparsity and spectrum constraints. J. Math. Imaging Vis. 52(1), 124–144 (2015)
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)
Villani, C.: Topics in Optimal Transportation. American Mathematical Society (2003)
Xia, G., Ferradans, S., Peyré, G., Aujol, J.: Synthesizing and mixing stationary gaussian texture models. SIAM J. Imaging Sci. 7(1), 476–508 (2014)
Acknowledgments
This project has been carried out with support from the French State, managed by the French National Research Agency (ANR-16-CE33-0010-01).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Leclaire, A., Rabin, J. (2019). A Fast Multi-layer Approximation to Semi-discrete Optimal Transport. In: Lellmann, J., Burger, M., Modersitzki, J. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2019. Lecture Notes in Computer Science(), vol 11603. Springer, Cham. https://doi.org/10.1007/978-3-030-22368-7_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-22368-7_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22367-0
Online ISBN: 978-3-030-22368-7
eBook Packages: Computer ScienceComputer Science (R0)