Abstract
We consider a variational model analyzed in March and Riey (Inverse Probl Imag 11(6): 997–1025, 2017) for simultaneous video inpainting and motion estimation. The model has applications in the field of recovery of missing data in archive film materials. A gray-value video content is reconstructed in a spatiotemporal region where the video data is lost. A variational method for motion compensated video inpainting is used, which is based on the simultaneous estimation of apparent motion in the video data. Apparent motion is mathematically described by a vector field of velocity, denoted optical flow, which is estimated through gray-value variations of the video data. The functional to be minimized is defined on a space of vector valued functions of bounded variation and the relaxation method of the Calculus of Variations is used. We introduce in the functional analyzed in March and Riey(Inverse Probl Imag 11(6): 997–1025, 2017) a suitable positive weight, and we show that diagonal minimizing sequences of the functional converge, up to subsequences as the weight tends to infinity, to minimizers of an appropriate limit functional. Such a limit functional is the relaxed version of a functional, modified with suitable improvements, proposed by Lauze and Nielsen (2004) and which permits an accurate joint reconstruction both of the optical flow and of the video content.
Similar content being viewed by others
References
Amar M, Chiricotto M, Giacomelli L, Riey G (2013) Mass-constrained minimization of a one-homogeneous functional arising in strain-gradient plasticity. J Math Anal Appl 397(1):381–401
Ambrosio L (1989) Variational problems in SBV and image segmentation. Acta Appl Math 17:1–40
Ambrosio L, Fusco N, Pallara D (2000) Functions of bounded variation and free discontinuity problems. Clarendon Press, Oxford
Anzellotti G (1985) The Euler equation for functionals with linear growth. Trans American Mat Soc 290(2):483–501
Anzellotti G (1986) On the minima of functionals with linear growth. Rendiconti del Seminario Matematico dell’Università, di Padova 75:91–110
Aubert G, Deriche R, Kornprobst P (1999) Computing optimal flow via variational techniques. SIAM J App Math 60(1):156–182
Aubert G, Kornprobst P (1999) A mathematical study of the relaxed optical flow problem in the space BV (Ω). SIAM J Math Anal 30(6):1282–1308
Aubert G, Kornprobst P (2006) Mathematical problems in image processing: partial differential equations and the calculus of variations, 2nd Edition. Springer, New York
Bertalmio M, Bertozzi A, Sapiro G (2001) Navier-Stokes, fluid-dynamics and image and video inpainting. In: Proceedings of computer vision and pattern recognition, vol 2001, pp 355–362
Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. In: Pajdla T, Matas J (eds) Proceedings of the 8th European conference on computer vision, vol 4. Springer, pp 25–36
Buttazzo G (1989) Semicontinuity, relaxation and integral representation in the calculus of variations pitman research notes in mathematics series, vol 207. Longman Scientific &Technical, UK
Carlsson JG, Carlsson E, Devulapalli R (2016) Shadow prices in territory division. Networks and Spatial Economics 16:893–931
Cocquerez JP, Chanas L, Blanc-Talon J (2003) Simultaneous inpainting and motion estimation of highly degraded video-sequences. In: Scandinavian conference on image analysis LNCS 2749, pp 523-530. Springer
Horn BKP, Schunck BG (1981) Determining optical flow. Artif Intell 17:185–203
Keller SH, Lauze F, Nielsen M (2008) Deintarlacing using variational methods. IEEE Trans Image Proc 17:2015–2028
Keller SH, Lauze F, Nielsen M (2011) Video super-resolution using simultaneous motion and intensity calculations. IEEE Trans Image Proc 20:1870–1884
Lauze F, Nielsen M (2004) A Variational algorithm for motion compensated inpainting. In: Barman S, Hoppe A, Ellis T (eds) British machine vision conference, vol 2. BMVA, pp 777–787
Low SH, Srikant R (2004) A mathematical framework for designing a low-loss, low-delay Internet. Networks and Spatial Economics 4:75101
March R, Riey G (2017) Analysis of a variational model for motion compensated inpainting. Inverse Probl Imag 11(6):997–1025
Peeta S, Ziliaskopoulos AK (2001) Foundations of dynamic traffic assignment: the past, the present and the future. Networks and Spatial Economics 1:233–265
Uras S, Girosi F, Verri A, Torre V (1988) Computational approach to motion perception. A Biol Cybern 60:79–87
Ziemer WP (1989) Weakly differentiable functions Springer - New York
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
March, R., Riey, G. Properties of a Variational Model for Video Inpainting. Netw Spat Econ 22, 315–326 (2022). https://doi.org/10.1007/s11067-019-09459-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11067-019-09459-4