Abstract
We present a novel algorithm for solving the image inpainting problem based on a field of locally interacting particle filters. Image inpainting, also known as image completion, is concerned with the problem of filling image regions with new visually plausible data. In order to avoid the difficulty of solving the problem globally for the region to be inpainted, we introduce a field of local particle filters. The states of the particle filters are image patches. Global consistency is enforced by a Markov random field image model which connects neighbouring particle filters. The benefit of using locally interacting particle filters is that several competing hypotheses on inpainting solutions are kept active, allowing the method to provide globally consistent solutions on problems where other local methods may fail. We provide examples of applications of the developed method.
Similar content being viewed by others
References
Ballester, C., Bertalmio, M., Caselles, V., Sapiro, G., Verdera, J.: Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans. Image Proc. 10(8), 1200–1211 (2001)
Bertalmio, M., Bertozzi, A., Sapiro, G.: Navier-stokes, fluid dynamics, and image and video inpainting. In: Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 355–362 (2001)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of SIGGRAPH, pp. 417–424. ACM (2000)
Chan, T., Shen, J.: Mathematical models for local nontexture inpainting. SIAM J. Appl. Math. 62(3), 1019–1043 (2002)
Chan, T., Kang, S.H., Shen, J.: Euler’s elastica and curvature-based inpainting. SIAM J. Appl. Math. 63(2), 564–592 (2002)
Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: Conference on Computer Vision and Pattern Recognition, CVPR’03, vol. 2, pp. 721–728 (2003)
Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Proc. 13(9), 1200–1212 (2004)
Doucet, A., Godsill, S., Andrieu, C.: On sequential Monte Carlo sampling methods for Bayesian filtering. Stat. Comput. 10(3), 197–208 (2000)
Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Proceedings of SIGGRAPH ’01, Los Angeles, California, USA, August (2001)
Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proceedings of 7th International Conference on Computer Vision 1999, pp. 1033–1038 (1999)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: IEEE Comput. Graph. Appl. 22(2), 56–65 (2002)
Griffin, L.D.: The second order local-image-structure solid. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1355–1366 (2007)
Grossauer, H., Scherzer, O.: Using the complex Ginzburg-Landau equation for digital inpainting in 2d and 3d. In: Proceedings of the Scale-Space Conference, pp. 225–236. Springer, Berlin (2003)
Gustavsson, D., Pedersen, K.S., Nielsen, M.: Geometric and texture inpainting by Gibbs sampling. In: Swedish Symposium on Image Analysis (SSBA ’07) (2007)
Gustavsson, D., Pedersen, K.S., Nielsen, M.: Image inpainting by cooling and heating. In: Ersbøll, B., Pedersen, K.S. (eds.) Scandinavian Conference on Image Analysis (SCIA ’07). Lecture Notes in Computer Science, vol. 4522, pp. 591–600. Springer, Berlin (2007)
Hays, J., Efros, A.A.: Scene completion using millions of photographs. In: International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2007 (2007)
Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)
Kittler, J., Föglein, J.: Contextual classification of multispectral pixel data. Image Vis. Comput. 2, 13–29 (1984)
Loog, M.: The jet metric. In: Sgallari et al. (eds.) Proceedings of SSVM07. Lecture Notes in Computer Science, vol. 4485, pp. 25–31. Springer, Berlin (2007)
Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vis. 7(1), 11–32 (1991)
Tschumperlé, D.: PDE’s based regularization of multivalued images and applications. Ph.D. thesis, Université de Nice-Sophia Antipolis, December (2002)
Winkler, G.: Image Analysis, Random Fields and Markov Chain Monte Carlo Methods: A Mathematical Introduction, 2nd edn. Springer, Berlin (2003)
Xin, J.H., Lee, S.M., Westland, S.: Evaluation of image similarity by histogram intersection. Color Res. Appl. 30(4), 265–274 (2005)
Zhu, S.C., Mumford, D.: Prior learning and gibbs reaction-diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 19(11), 1236–1250 (1997)
Zhu, S.C., Wu, Y.N., Mumford, D.: Minimax entropy principle and its application to texture modelling. Neural Comput. 9(8), 1627–1660 (1997)
Zhu, S.C., Wu, Y.N., Mumford, D.: Filters, random fields, and maximum entropy (frame): Towards a unified theory for texture modeling. Int. J. Comput. Vis. 27(2), 107–126 (1998)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cuzol, A., Pedersen, K.S. & Nielsen, M. Field of Particle Filters for Image Inpainting. J Math Imaging Vis 31, 147–156 (2008). https://doi.org/10.1007/s10851-008-0072-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-008-0072-7