Abstract
In this article we consider macrocanonical models for texture synthesis. In these models samples are generated given an input texture image and a set of features which should be matched in expectation. It is known that if the images are quantized, macrocanonical models are given by Gibbs measures, using the maximum entropy principle. We study conditions under which this result extends to real-valued images. If these conditions hold, finding a macrocanonical model amounts to minimizing a convex function and sampling from an associated Gibbs measure. We analyze an algorithm which alternates between sampling and minimizing. We present experiments with neural network features and study the drawbacks and advantages of using this sampling scheme.
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
Atchadé, Y.F., Fort, G., Moulines, E.: On perturbed proximal gradient algorithms. J. Mach. Learn. Res. 18, 310–342 (2017). Paper No. 10, 33
Bruna, J., Mallat, S.: Multiscale sparse microcanonical models. arXiv e-prints, arXiv:1801.02013, January 2018
Cano, D., Minh, T.: Texture synthesis using hierarchical linear transforms. Signal Process. 15(2), 131–148 (1988)
De Bortoli, V., Durmus, A., Pereyra, M., Fernandez Vidal, A.: Stochastic optimization with unadjusted kernel: the SOUK algorithm (2019, preprint)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: ICCV, pp. 1033–1038 (1999)
Gagalowicz, A., Ma, S.D.: Model driven synthesis of natural textures for 3-D scenes. Comput. Graph. 10(2), 161–170 (1986)
Galerne, B., Leclaire, A., Rabin, J.: A texture synthesis model based on semi-discrete optimal transport in patch space. SIIMS 11(4), 2456–2493 (2018)
Galerne, B., Gousseau, Y., Morel, J.: Random phase textures: theory and synthesis. IEEE Trans. Image Process. 20(1), 257–267 (2011)
Gatys, L.A., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: NIPS, pp. 262–270 (2015)
Gatys, L.A., Ecker, A.S., Bethge, M., Hertzmann, A., Shechtman, E.: Controlling perceptual factors in neural style transfer. In: CVPR, pp. 3730–3738 (2017)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.J.: A kernel method for the two-sample-problem. In: NIPS, pp. 513–520 (2006)
Heeger, D.J., Bergen, J.R.: Pyramid-based texture analysis/synthesis. In: ICIP, pp. 648–651 (1995)
Jaynes, E.T.: Information theory and statistical mechanics. Phys. Rev. 106, 620–630 (1957)
Jetchev, N., Bergmann, U., Vollgraf, R.: Texture synthesis with spatial generative adversarial networks. CoRR (2016)
Liu, G., Gousseau, Y., Xia, G.: Texture synthesis through convolutional neural networks and spectrum constraints. In: ICPR, pp. 3234–3239 (2016)
Lu, Y., Zhu, S., Wu, Y.N.: Learning FRAME models using CNN filters. In: AAAI, pp. 1902–1910 (2016)
Ogden, H.E.: A sequential reduction method for inference in generalized linear mixed models. Electron. J. Stat. 9(1), 135–152 (2015)
Peyré, G.: Texture synthesis with grouplets. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 733–746 (2010)
Portilla, J., Simoncelli, E.P.: A parametric texture model based on joint statistics of complex wavelet coefficients. IJCV 40(1), 49–70 (2000)
Raad, L., Davy, A., Desolneux, A., Morel, J.: A survey of exemplar-based texture synthesis. Ann. Math. Sci. Appl. 3, 89–148 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR (2014)
Ulyanov, D., Lebedev, V., Vedaldi, A., Lempitsky, V.S.: Texture networks: Feed-forward synthesis of textures and stylized images. In: ICML, pp. 1349–1357 (2016)
Ustyuzhaninov, I., Brendel, W., Gatys, L.A., Bethge, M.: Texture synthesis using shallow convolutional networks with random filters. CoRR (2016)
van Wijk, J.J.: Spot noise texture synthesis for data visualization. In: SIGGRAPH, pp. 309–318 (1991)
Zhu, S.C., Wu, Y.N., Mumford, D.: Filters, random fields and maximum entropy (FRAME): towards a unified theory for texture modeling. IJCV 27(2), 107–126 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
De Bortoli, V., Desolneux, A., Galerne, B., Leclaire, A. (2019). Macrocanonical Models for Texture Synthesis. 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_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-22368-7_2
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)