Abstract
This paper proposes a new definition of the averaging of discrete probability distributions as a barycenter over the Monge-Kantorovich optimal transport space. To overcome the time complexity involved by the numerical solving of such problem, the original Wasserstein metric is replaced by a sliced approximation over 1D distributions. This enables us to introduce a new fast gradient descent algorithm to compute Wasserstein barycenters of point clouds.
This new notion of barycenter of probabilities is likely to find applications in computer vision where one wants to average features defined as distributions. We show an application to texture synthesis and mixing, where a texture is characterized by the distribution of the response to a multi-scale oriented filter bank. This leads to a simple way to navigate over a convex domain of color textures.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Villani, C.: Topics in Optimal Transportation. American Math. Society (2003)
Rubner, Y., Tomasi, C., Guibas, L.J.: The Earth Mover’s Distance as a Metric for Image Retrieval. International Journal of Computer Vision 40, 99–121 (2000)
Pitié, F., Kokaram, A.: The Linear Monge-Kantorovitch Colour Mapping for Example-Based Colour Transfer. In: Proc. of CVMP 2006 (2006)
Dominitz, A., Tannenbaum, A.: Texture mapping via optimal mass transport. IEEE Transactions on Visualization and Computer Graphics 16, 419–433 (2009)
Delon, J.: Movie and video scale-time equalization application to flicker reduction. IEEE Trans. Image Proc. 15, 241–248 (2006)
Ambrosio, L., Caffarelli, L.A., Brenier, Y., Buttazzo, G., Villani, C.: Optimal Transportation and Applications. Mathematics and statistics edn. Lecture Notes in Mathematics, vol. 1813. Springer, Heidelberg (2003)
Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proc. of ICCV 1999, p. 1033 (1999)
Wei, L.Y., Levoy, M.: Fast texture synthesis using tree-structured vector quantization. In: Proc. Siggraph 2000, pp. 479–488 (2000)
Efros, A., Freeman, W.: Image quilting for texture synthesis and transfer. ACM Trans. on Graphics, 341–346 (2001)
Ashikhmin, M.: Synthesizing natural textures. In: SI3D 2001: Proceedings of the 2001 Symposium on Interactive 3D Graphics, pp. 217–226 (2001)
Lefebvre, S., Hoppe, H.: Parallel controllable texture synthesis. ACM Trans. on Graphics 24, 777–786 (2005)
Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: Texture optimization for example-based synthesis. ACM Trans. on Graphics 24, 795–802 (2005)
Kwatra, V., Schdl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: Image and video synthesis using graph cuts. ACM Trans. on Graphics 22, 277–286 (2003)
Perlin, K.: An image synthesizer. In: Proc. Siggraph 1985, pp. 287–296. ACM Press, New York (1985)
Bonet, J.S.D.: Multiresolution sampling procedure for analysis and synthesis of texture images. In: Proc. Siggraph 1997, pp. 361–368. ACM Press, New York (1997)
Paget, R., Longstaff, I.D.: Texture synthesis via a noncausal nonparametric multiscale markov random field. IEEE Trans. Image Proc. 7, 925–931 (1998)
Mumford, D., Gidas, B.: Stochastic models for generic images. Q. Appl. Math. LIV, 85–111 (2001)
Heeger, D.J., Bergen, J.R.: Pyramid-Based texture analysis/synthesis. In: Proc. Siggraph 1995. Annual Conference Series, ACM SIGGRAPH, pp. 229–238 (1995)
Cook, R., DeRose, T.: Wavelet noise. ACM Trans. on Graphics 24, 803–811 (2005)
Portilla, J., Simoncelli, E.P.: A parametric texture model based on joint statistics of complex wavelet coefficients. Int. Journal of Computer Vision 40, 49–70 (2000)
Bar-Joseph, Z., El-Yaniv, R., Lischinski, D., Werman, M.: Texture mixing and texture movie synthesis using statistical learning. IEEE Transactions on Visualization and Computer Graphics 7, 120–135 (2001)
Peyré, G.: Texture synthesis with grouplets. IEEE Trans. Patt. Anal. and Mach. Intell. 32, 733–746 (2010)
Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image analogies. In: ACM (ed.) Proc. Siggraph 2001, pp. 327–340. ACM Press, New York (2001)
Liu, Z., Liu, C., Shum, H.Y., Yu, Y.: Pattern-based texture metamorphosis. In: Proc. Pacific Graphics 2002, pp. 184–193. IEEE Computer Society, Los Alamitos (2002)
Tonietto, L., Walter, M.: Texture metamorphosis driven by texton masks. Computers and Graphics 29, 697–703 (2005)
Tal, A., Elber, G.: Image morphing with feature preserving texture. Comput. Graph. Forum 18, 339–348 (1999)
Matusik, W., Zwicker, M., Durand, F.: Texture design using a simplicial complex of morphable textures. ACM Trans. on Graphics 24, 787–794 (2005)
Burkard, R., Dell’Amico, M., Martello, S.: Assignment Problems. SIAM, Philadelphia (2009)
Rabin, J., Peyré, G., Cohen, L.D.: Geodesic shape retrieval via optimal mass transport. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 771–784. Springer, Heidelberg (2010)
Dowson, D.C., Landau, B.V.: The Fréchet distance between multivariate normal distributions. Journal of Multivariate Analysis 12, 450–455 (1982)
Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. To appear in SIAM Journal on Mathematical Analysis (2011)
Simoncelli, E.P., Freeman, W.T., Adelson, E.H., Heeger, D.J.: Shiftable multiscale transforms. IEEE Trans. Info. Theory 38, 587–607 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rabin, J., Peyré, G., Delon, J., Bernot, M. (2012). Wasserstein Barycenter and Its Application to Texture Mixing. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2011. Lecture Notes in Computer Science, vol 6667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24785-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-24785-9_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24784-2
Online ISBN: 978-3-642-24785-9
eBook Packages: Computer ScienceComputer Science (R0)