Abstract
We propose a new video inpainting model for movies restoration application. Our model combines structural reconstruction with a diffusion-based method and textural reconstruction with a patch-based method. Both proposed energies (one for each method) are alternatively minimized in order to preserve the overall structure while adding textural refinement. While the structural reconstruction is obtained jointly with optical flow computation with several proximal approaches, the textural reconstruction is processed by a variational non-local approach. Preliminary results on different Middlebury frames show quality improvement in the reconstruction.
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
Arias, P., Facciolo, G., Caselles, V., Sapiro, G.: A variational framework for exemplar-based image inpainting. IJCV 93, 319–347 (2011)
Aubert, G., Deriche, R., Kornprobst, P.: Computing optical flow via variational techniques. SIAM J. Appl. Math. 60, 156–182 (1999)
Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM TOG 28 (2009)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings SIGGRAPH (2000)
Buades, A., Lisani, J.L.: Video Denoising with optical flow estimation. IPOL 8, 142–166 (2018)
Bugeau, A., Bertalmio, M.: Combining texture synthesis and diffusion for image inpainting. In: Proceedings VISAPP (2009)
Burger, M., Dirks, H., Schönlieb, C.B.: A variational model for joint motion estimation and image reconstruction. SIAM J. Imag. Sc. 11, 94–128 (2018)
Buyssens, P., Daisy, M., Tschumperlé, D., Lézoray, O.: Exemplar-based inpainting: technical review and new heuristics for better geometric reconstructions. IEEE TIP 24, 1809–1824 (2015)
Cao, F., Gousseau, Y., Masnou, S., Pérez, P.: Geometrically guided exemplar-based inpainting. SIAM J. Appl. Math. 4, 1143–1179 (2011)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. JMIV 40, 120–145 (2011)
Chan, T.F., Shen, J.: Local inpainting models and TV inpainting. SIAM J. Appl. Math. 62 (2001)
Cocquerez, J.P., Chanas, L., Blanc-Talon, J.: Simultaneous inpainting and motion estimation of highly degraded video-sequences. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 685–692. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-45103-X_91
Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE TIP 13, 1200–1212 (2004)
Do, V., Lebrun, G., Malapert, L., Smet, C., Tschumperlé, D.: Inpainting d’images couleurs par lissage anisotrope et synthèse de textures. In: Proceedings RFIA (2006)
Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proceedings ICCV (1999)
Horn, B.K., Schunck, B.G.: Determining optical flow. AI 17, 185–203 (1981)
Lauze, F., Nielsen, M.: A variational algorithm for motion compensated inpainting. In: Proceedings BMVC (2004)
Lauze, F., Nielsen, M.: On variational methods for motion compensated inpainting. arXiv preprint (2009)
Le, T., Almansa, A., Gousseau, Y., Masnou, S.: Motion-consistent video inpainting. In: Proceedings ICIP (2017)
March, R., Riey, G.: Analysis of a variational model for motion compensated inpainting. Inverse Prob. Imaging 11, 997–1025 (2017)
Masnou, S., Morel, J.M.: Level lines based disocclusion. In: Proceedings ICIP (1998)
Newson, A., Almansa, A., Fradet, M., Gousseau, Y., Pérez, P.: Video inpainting of complex scenes. SIAM J. Imag. Sci. 7 (2014)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74936-3_22
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
Renaudeau, A., Lauze, F., Pierre, F., Aujol, JF., Durou, JD. (2019). Alternate Structural-Textural Video Inpainting for Spot Defects Correction in Movies. 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_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-22368-7_9
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)