Towards fast, generic video inpainting

Newson, A.; Almansa, A.; Fradet, M.; Gousseau, Y.; Pérez, P.

doi:10.1145/2534008.2534019

by A. Newson, A. Almansa, M. Fradet, Y. Gousseau, P. Pérez

Abstract:

Achieving globally coherent video inpainting results in reasonable time and in an automated manner is still an open problem. In this paper, we build on the seminal work by Wexler et al. to propose an automatic video inpainting algorithm yielding convincing results in greatly reduced computational times. We extend the PatchMatch algorithm to the spatio-temporal case in order to accelerate the search for approximate nearest neighbours in the patch space. We also provide a simple and fast solution to the well known over-smoothing problem resulting from the averaging of patches. Furthermore, we show that results similar to those of a supervised state-of-the-art method may be obtained on high resolution videos without any manual intervention. Our results indicate that globally coherent patch-based algorithms are feasible and an attractive solution to the difficult problem of video inpainting. \textcopyright 2013 ACM.

Reference:

Towards fast, generic video inpainting (A. Newson, A. Almansa, M. Fradet, Y. Gousseau, P. Pérez), In Proceedings of the 10th European Conference on Visual Media Production (CVMP), ACM Press, 2013.

Bibtex Entry:

@inproceedings{Newson2013a,
	Abstract = {Achieving globally coherent video inpainting results in reasonable time and in an automated manner is still an open problem. In this paper, we build on the seminal work by Wexler et al. to propose an automatic video inpainting algorithm yielding convincing results in greatly reduced computational times. We extend the PatchMatch algorithm to the spatio-temporal case in order to accelerate the search for approximate nearest neighbours in the patch space. We also provide a simple and fast solution to the well known over-smoothing problem resulting from the averaging of patches. Furthermore, we show that results similar to those of a supervised state-of-the-art method may be obtained on high resolution videos without any manual intervention. Our results indicate that globally coherent patch-based algorithms are feasible and an attractive solution to the difficult problem of video inpainting. {\textcopyright} 2013 ACM.},
	Address = {London, UK},
	Author = {Newson, A. and Almansa, A. and Fradet, M. and Gousseau, Y. and P{\'{e}}rez, P.},
	Booktitle = {Proceedings of the 10th European Conference on Visual Media Production (CVMP)},
	Doi = {10.1145/2534008.2534019},
	Isbn = {9781450325899},
	Keywords = {PatchMatch,exemplar-based,patches,space-time occlusion,video inpainting},
	Publisher = {ACM Press},
	Title = {{Towards fast, generic video inpainting}},
	Year = {2013},
	Bdsk-Url-1 = {https://doi.org/10.1145/2534008.2534019}}