Abstract
We present a new biomimetic image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in Boscain et al. (SIAM J. Imaging Sci. 7(2):669–695, 2014) and based upon a semi-discrete variation of the Citti–Petitot–Sarti model of the primary visual cortex V1. The AHE algorithm is based on a suitable combination of sub-Riemannian hypoelliptic diffusion and ad hoc local averaging techniques. In particular, we focus on highly corrupted images (i.e., where more than the 80% of the image is missing), for which we obtain high-quality reconstructions.
Similar content being viewed by others
Notes
More precisely, in [9, Theorem 26] the authors prove that given a Gaussian function G and a bounded domain \(\mathcal D\subset \mathbb {R}^2\), the set of square integrable functions \(f\in L^2(\mathcal D)\) such that \(f\star G\) is a Morse function is a countable intersection of open-dense sets. See also [9, Theorem 28] for a slightly stronger result.
References
Abas, F.: Analysis of craquelure patterns for content-based retrieval. PhD thesis, University of Southampton (2004)
Agrachev, A., Barilari, D., Boscain, U.: Introduction to Riemannian and Sub-Riemannian Geometry (Lecture Notes). http://webusers.imj-prg.fr/~davide.barilari/notes.php
Bellaïche, A.: The tangent space in sub-Riemannian geometry. In: Sub-Riemannian Geometry, volume 144 of Progress in Mathematics, pp. 1–78. Birkhäuser, Basel (1996)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of SIGGRAPH 2000, New Orleans, USA, pp. 417–424 (2000)
Bohi, A., Prandi, D., Guis, V., Bouchara, F., Gauthier, J.-P.: Fourier descriptors based on the structure of the human primary visual cortex with applications to object recognition. J. Math. Imaging Vis. 57(1), 117–133 (2017)
Boscain, U., Charlot, G., Rossi, F.: Existence of planar curves minimizing length and curvature. Proc. Steklov Inst. Math. 270, 43–56 (2010)
Boscain, U., Chertovskih, R.A., Gauthier, J.-P., Remizov, A.O.: Hypoelliptic diffusion and human vision: a semidiscrete new twist. SIAM J. Imaging Sci. 7(2), 669–695 (2014)
Boscain, U., Duits, R., Rossi, F., Sachkov, Yu.: Curve cuspless reconstruction via sub-Riemannian geometry. ESAIM Control Optim. Calc. Var. 20(3), 748–770 (2014)
Boscain, U., Duplaix, J., Gauthier, J.-P., Rossi, F.: Anthropomorphic image reconstruction via hypoelliptic diffusion. SIAM J. Control Optim. 50(3), 1–25 (2012)
Boscain, U., Gauthier, J.-P., Prandi, D., Remizov, A.: Image reconstruction via non-isotropic diffusion in Dubins/Reed-Shepp-like control systems. In: 53rd IEEE Conference on Decision and Control, pp. 4278–4283 (2014)
Bugeau, A., Bertalmío, M., Caselles, V., Sapiro, G.: A comprehensive framework for image inpainting. IEEE Trans. Image Process. 19(10), 2634–2645 (2010)
Chan, T.F., Kang, S.H., Shen, J.: Euler’s elastica and curvature-based inpainting. SIAM J. Appl. Math. 63(2), 564–592 (2002)
Citti, G., Franceschiello, B., Sanguinetti, G., Sarti, A.: Sub-Riemannian mean curvature flow for image processing. SIAM J. Imaging Sci. 9(1), 212–237 (2016)
Citti, G., Sarti, A.: A cortical based model of perceptual completion in the roto-translation space. J. Math. Imaging Vis. 24(3), 307–326 (2006)
Cornelis, B., Ružić, T., Gezels, E., Dooms, A., Pižurica, A., Platiša, L., Cornelis, J., Martens, M., De Mey, M., Daubechies, I.: Crack detection and inpainting for virtual restoration of paintings: the case of the ghent altarpiece. Signal Process. 93(3), 605–619 (2013)
Duits, R., Boscain, U., Rossi, F., Sachkov, Y.: Association fields via cuspless sub-Riemannian geodesics in SE(2). J. Math. Imaging Vis. 49(2), 384–417 (2014)
Duits, R., Franken, E.: Left-invariant parabolic evolutions on \({\rm SE}(2)\) and contour enhancement via invertible orientation scores. Part I: linear left-invariant diffusion equations on \({\rm SE}(2)\). Q. Appl. Math. 68(2), 255–292 (2010)
Duits, R., Franken, E.: Left-invariant parabolic evolutions on \({\rm SE}(2)\) and contour enhancement via invertible orientation scores. Part II: nonlinear left-invariant diffusions on invertible orientation scores. Q. Appl. Math. 68(2), 293–331 (2010)
Duits, R., van Almsick, M.A.: The explicit solutions of linear left-invariant second order stochastic evolution equations on the 2D euclidean motion group. Q. Appl. Math. 66, 27–67 (2008)
Facciolo, G., Arias, P., Caselles, V., Sapiro, G.: Exemplar-based interpolation of sparsely sampled images. In: Cremers, D., Boykov, Yu., Blake, A., Schmidt, F.R. (eds.) Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference EMMCVPR 2009 (Bonn, Germany, August 24–27, 2009) Proceedings, pp. 331–344. Springer (2009)
Ferziger, J.H., Perić, M.: Computational Methods for Fluid Dynamics, 3rd rev. edn. Springer, Berlin (2002)
Gromov, M.: Carnot-Carathéodory spaces seen from within. In: Sub-Riemannian Geometry, volume 144 of Progress in Mathematics, pp. 79–323. Birkhäuser, Basel (1996)
Hladky, R.K., Pauls, S.D.: Minimal surfaces in the roto-translation group with applications to a neuro-biological image completion model. J. Math. Imaging Vis. 36(1), 1–27 (2010)
Hörmander, L.: Hypoelliptic second order differential equations. Acta Math. 119, 147–171 (1967)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148, 574–591 (1959)
Marchuk, G.I.: Methods of Numerical Mathematics. Springer, Berlin (1982)
Marr, D., Hildreth, E.: Theory of edge detection. Proc. R. Soc. Lond. B Biol. Sci. 207(1167), 187–217 (1980)
Masnou, S.: Disocclusion: a variational approach using level lines. IEEE Trans. Image Process. 11(2), 68–76 (2002)
Masnou, S., Morel, J.-M.: Level lines based disocclusion. In: Proceedings of 5th IEEE International Confernce on Image Processing, vol. 3, pp. 259–263 (1998)
Montgomery, R.: A Tour of Subriemannian Geometries, Their Geodesics and applications, volume 91 of Mathematical Surveys and Monographs. American Mathematical Society, Providence, RI (2002)
Peichl, L., Wässle, H.: Size, scatter and coverage of ganglion cell receptive field centres in the cat retina. J. Physiol. 291, 117–141 (1979)
Petitot, J.: The neurogeometry of pinwheels as a sub-Riemannian contact structure. J. Physiol. Paris 97(2–3), 265–309 (2003)
Petitot, J.: Neurogéométrie de la vision - Modèles mathématiques et physiques des architectures fonctionnelles. Les Éditions de l’École Polytechnique (2008)
Ponomarenko, N., Jin, L., Lukin, V., Egiazarian, K.: Self-similarity measure for assessment of image visual quality. In: Proceedings of the 13th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS’11, pp. 459–470, Berlin, Heidelberg (2011)
Prandi, D., Boscain, U., Gauthier, J.-P.: Image processing in the semidiscrete group of rototranslations. In: Geometric Science of Information, volume 9389 of Lecture Notes in Computer Science, pp. 627–634. Springer (2015)
Prandi, D., Gauthier, J.-P.: A semidiscrete version of the Petitot model as a plausible model for anthropomorphic image reconstruction and pattern recognition. Springer Briefs in Mathematics. Springer. arXiv:1704.03069
Sanguinetti, G., Citti, G., Sarti, A.: Image completion using a diffusion driven mean curvature flow in a sub-Riemannian space. In: Proceedings of the 3rd International Conference on Computer Vision Theory and Applications (VISAPP 2008), volume 2, pp. 46–53 (2008)
Strichartz, R.S.: Sub-Riemannian geometry. J. Differ. Geom. 24(2), 221–263 (1986)
Strichartz, R.S.: Corrections to: Sub-Riemannian geometry [J. Differential Geom. 24(2), 221–263 (1986); MR0862049 (88b:53055)]. J. Differ. Geom. 30(2), 595–596 (1989)
Voronin, V.V., Frantc, V.A., Marchuk, V.I., Sherstobitov, A.I., Egiazarian, K.: No-reference visual quality assessment for image inpainting. In: Proceedings of SPIE 9399, Image Processing: Algorithms and Systems XIII (March 16, 2015), p. 93990U (2015)
Wang, M., Yan, B., Ngan, K.N.: An efficient framework for image/video inpainting. Signal Process. Image Commun. 28(7), 753–762 (2013)
Zhang, F., Li, S., Ma, L., Ngan, K.N.: Limitation and challenges of image quality measurement. In: Proceedings of SPIE 7744, Visual Communications and Image Processing 2010 (July 13, 2010), pp. 774402–774402–8 (2010)
Acknowledgements
We deeply thank G. Facciolo, S. Masnou and G.P. Panasenko for their help. This work was supported by the ERC POC project ARTIV1 contract number 727283, by the ANR project “SRGI” ANR-15-CE40-0018, by a public grant as part of the Investissement d’avenir project, reference ANR-11-LABX-0056-LMH, LabEx LMH (in a joint call with Programme Gaspard Monge en Optimisation et Recherche Opérationnelle), by the iCODE institute, research project of the Idex Paris-Saclay, by the POCI-01-0145-FEDER-006933/SYSTEC project financed by ERDF and FCT through COMPETE2020.
Author information
Authors and Affiliations
Corresponding author
Appendix A: Sub-Riemannian Geometry
Appendix A: Sub-Riemannian Geometry
In this Appendix, we recall some standard definitions of sub-Riemannian geometry and hypoelliptic operators. Classical texts are [2, 3, 22, 30].
Definition 1
A (n, m)-sub-Riemannian manifold is given by a triple \((M,{\blacktriangle },{\mathbf {g}})\), where
-
M is a connected smooth manifold of dimension n;
-
\({\blacktriangle }\) is a smooth distribution of constant rank \(m< n\) satisfying the Hörmander condition. That is, \({\blacktriangle }\) is a smooth map that associates to \(q\in M\) an m-dimensional subspace \({\blacktriangle }(q)\) of \(T_qM\), such that \(\forall ~q\in M\) we have
$$\begin{aligned} T_qM={{{\mathrm{span}}}}\lbrace [X_1,[\ldots [X_{k-1},X_k]]](q)~|~X_i\in \mathrm {Vec}_H(M)\rbrace . \end{aligned}$$Here, \(\mathrm {Vec}_H(M)\) denotes the set of horizontal smooth vector fields on M, i.e.,
$$\begin{aligned} \mathrm {Vec}_H(M)=\lbrace X\in \mathrm {Vec}(M)\ |\ X(q)\in {\blacktriangle }(q)~\ \forall ~q\in M\rbrace . \end{aligned}$$ -
\({\mathbf {g}}_q\) is a Riemannian metric on \({\blacktriangle }(q)\), smooth as function of q.
A Lipschitz continuous curve \(q(\cdot ):[0,T]\rightarrow M\) is said to be horizontal if \(\dot{q}(t)\in {\blacktriangle }(q(t))\) for almost every \(t\in [0,T]\). Given an horizontal curve \(q(\cdot ):[0,T]\rightarrow M\), the length of \(q(\cdot )\) is
The distance induced by the sub-Riemannian structure on M is the function
The connectedness assumption for M and the Hörmander condition guarantee the finiteness and the continuity of \(d(\cdot ,\cdot )\) with respect to the topology of M (Chow’s Theorem, see for instance [2]). The function \(d(\cdot ,\cdot )\) is called the Carnot-Carathéodory distance and gives to M the structure of metric space.
Locally, the pair \(({\blacktriangle },{\mathbf {g}})\) can be specified by assigning a set of m smooth vector fields spanning \({\blacktriangle }\), that are moreover orthonormal for \({\mathbf {g}}\), i.e.,
Such a set \(\lbrace X_1,\ldots ,X_m\rbrace \) is called a local orthonormal frame for the sub-Riemannian structure. When \(({\blacktriangle },{\mathbf {g}})\) can be defined by m globally defined vector fields as in (14) we say that the sub-Riemannian manifold is trivializable.
Given a trivializable (n, m)-sub-Riemannian manifold, the problem of finding a curve realizing the distance between two fixed points \(q_0,q_1\in M\) is naturally formulated as the following optimal control problem
1.1 A.1 Diffusion in a Sub-Riemannian Manifold
Given a sub-Riemannian manifold \((M,{\blacktriangle },{\mathbf {g}})\) and a smooth volume \(\omega \) on M, the sub-Riemannian heat equation is the diffusion equation:
where \(\varDelta _H\) is the sub-Riemannian (or horizontal) Laplacian, defined by
Here, \({{\mathrm{div}}}_\omega \) is the divergence with respect to the volume \(\omega \) and \({{\mathrm{grad}}}_H\varphi \) is the horizontal gradient of \(\varphi \). That is, it is the unique vector field satisfying, for every \(q\in M\),
If \(\lbrace X_1,\ldots ,X_m\rbrace \) is a local orthonormal frame, it follows that \({{\mathrm{grad}}}_H \varphi = \sum _{i=1}^m(X_i\varphi )X_i\), and thus that
Thanks to the Hörmander condition assumed in the definition of the sub-Riemannian manifold, the celebrated Hörmander Theorem [24], implies the following.
Theorem 1
The operators \(\varDelta _H\) (operating on functions \(\varphi :M\rightarrow \mathbb {R}\)) and \(\varDelta _H-\partial _t\) (operating on functions \(\psi :M\times \mathbb {R}\rightarrow \mathbb {R}\)) are hypoelliptic.
We recall that a second-order differential operator L is said to be hypoelliptic if for every distribution \(\varphi \) defined on an open set \(\Omega \) of a manifold N, the condition \(L\varphi \in {C}^\infty (\Omega )\) implies that \(\varphi \in {C}^\infty (\Omega )\). In particular, the hypoellipticity of \(\varDelta _H-\partial _t\) implies that any solution to the heat equation (15) on \( M\times ]t_0,t_1[\) is smooth.
Remark 2
The sub-Riemannian structure studied in this paper is the one on \(PT\mathbb {R}^2\) for which the distribution is given by the vector fields
The metric \(\mathbf {g}\) is then chosen such that \(\lbrace X_1,X_2\rbrace \) are orthogonal, and \({\mathbf {g}}(X_1,X_1)=1\), \({\mathbf {g}}(X_2,X_2)=1/\beta \), for some given \(\beta >0\). By taking as volume on \(PT\mathbb {R}^2\) the Lebesgue measure, i.e., \(\omega = dx\,dy\,d\theta \), since \(X_1\) and \(X_2\) are divergence free, one immediately gets
Rights and permissions
About this article
Cite this article
Boscain, U.V., Chertovskih, R., Gauthier, JP. et al. Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion. J Math Imaging Vis 60, 1231–1245 (2018). https://doi.org/10.1007/s10851-018-0810-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-018-0810-4