by Alasdair Newson, Andrés Almansa, Matthieu Fradet, Yann Gousseau, Patrick Pérez
Abstract:
We propose an automatic video inpainting algorithm which relies on the optimisation of a global, patch-based functional. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background. Furthermore, we achieve this in an order of magnitude less execution time with respect to the state-of-the-art. We are also able to achieve good quality results on high definition videos. Finally, we provide specific algorithmic details to make implementation of our algorithm as easy as possible. The resulting algorithm requires no segmentation or manual input other than the definition of the inpainting mask, and can deal with a wider variety of situations than is handled by previous work.
Reference:
Video Inpainting of Complex Scenes (Alasdair Newson, Andrés Almansa, Matthieu Fradet, Yann Gousseau, Patrick Pérez), In SIAM Journal on Imaging Sciences, volume 7, 2014.
Bibtex Entry:
@article{Newson2014:SIIMS-VideoInpainting,
Abstract = {We propose an automatic video inpainting algorithm which relies on the optimisation of a global, patch-based functional. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background. Furthermore, we achieve this in an order of magnitude less execution time with respect to the state-of-the-art. We are also able to achieve good quality results on high definition videos. Finally, we provide specific algorithmic details to make implementation of our algorithm as easy as possible. The resulting algorithm requires no segmentation or manual input other than the definition of the inpainting mask, and can deal with a wider variety of situations than is handled by previous work.},
Annote = {http://hal.archives-ouvertes.fr/hal-00937795 },
Author = {Newson, Alasdair and Almansa, Andr\'{e}s and Fradet, Matthieu and Gousseau, Yann and P\'{e}rez, Patrick},
Date-Added = {2015-02-18 16:30:02 +0000},
Date-Modified = {2015-02-18 18:56:18 +0000},
Doi = {10.1137/140954933},
File = {:Users/almansa/Documents/Mendeley Desktop/PDFs/Newson et al. - 2014 - Video Inpainting of Complex Scenes.pdf:pdf;::},
Issn = {1936-4954},
Journal = {SIAM Journal on Imaging Sciences},
Month = oct,
Number = {4},
Pages = {1993--2019},
Title = {{Video Inpainting of Complex Scenes}},
Url = {http://perso.telecom-paristech.fr/~almansa/video_inpainting/},
Volume = {7},
Year = {2014},
Bdsk-Url-1 = {http://hal.archives-ouvertes.fr/hal-00937795%20http://perso.telecom-paristech.fr/~almansa/video%5C_inpainting/},
Bdsk-Url-2 = {http://dx.doi.org/10.1137/140954933}}