Home > Research > Publications & Outputs > How not to be seen
View graph of relations

How not to be seen: object removal from videos of crowded scenes

Research output: Contribution to journalJournal article

Published

Standard

How not to be seen : object removal from videos of crowded scenes. / Granados, Miguel; Tompkin, James; Kim, Kwang In; Grau, Oliver; Kautz, Jan; Theobalt, Christian.

In: Computer Graphics Forum, Vol. 31, No. 2 Pt 1, 05.2012, p. 219-228.

Research output: Contribution to journalJournal article

Harvard

Granados, M, Tompkin, J, Kim, KI, Grau, O, Kautz, J & Theobalt, C 2012, 'How not to be seen: object removal from videos of crowded scenes', Computer Graphics Forum, vol. 31, no. 2 Pt 1, pp. 219-228. https://doi.org/10.1111/j.1467-8659.2012.03000.x

APA

Granados, M., Tompkin, J., Kim, K. I., Grau, O., Kautz, J., & Theobalt, C. (2012). How not to be seen: object removal from videos of crowded scenes. Computer Graphics Forum, 31(2 Pt 1), 219-228. https://doi.org/10.1111/j.1467-8659.2012.03000.x

Vancouver

Granados M, Tompkin J, Kim KI, Grau O, Kautz J, Theobalt C. How not to be seen: object removal from videos of crowded scenes. Computer Graphics Forum. 2012 May;31(2 Pt 1):219-228. https://doi.org/10.1111/j.1467-8659.2012.03000.x

Author

Granados, Miguel ; Tompkin, James ; Kim, Kwang In ; Grau, Oliver ; Kautz, Jan ; Theobalt, Christian. / How not to be seen : object removal from videos of crowded scenes. In: Computer Graphics Forum. 2012 ; Vol. 31, No. 2 Pt 1. pp. 219-228.

Bibtex

@article{b71a9b5a07dc477e8b53405411c46056,
title = "How not to be seen: object removal from videos of crowded scenes",
abstract = "Removing dynamic objects from videos is an extremely challenging problem that even visual effects professionals often solve with time-consuming manual frame-by-frame editing. We propose a new approach to video completion that can deal with complex scenes containing dynamic background and non-periodical moving objects. We build upon the idea that the spatio-temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible. Video completion is performed by solving a large combinatorial problem that searches for an optimal pattern of pixel offsets from occluded to unoccluded regions. Our contribution includes an energy functional that generalizes well over different scenes with stable parameters, and that has the desirable convergence properties for a graph-cut-based optimization. We provide an interface to guide the completion process that both reduces computation time and allows for efficient correction of small errors in the result. We demonstrate that our approach can effectively complete complex, high-resolution occlusions that are greater in difficulty than what existing methods have shown.",
author = "Miguel Granados and James Tompkin and Kim, {Kwang In} and Oliver Grau and Jan Kautz and Christian Theobalt",
year = "2012",
month = "5",
doi = "10.1111/j.1467-8659.2012.03000.x",
language = "English",
volume = "31",
pages = "219--228",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",
number = "2 Pt 1",

}

RIS

TY - JOUR

T1 - How not to be seen

T2 - object removal from videos of crowded scenes

AU - Granados, Miguel

AU - Tompkin, James

AU - Kim, Kwang In

AU - Grau, Oliver

AU - Kautz, Jan

AU - Theobalt, Christian

PY - 2012/5

Y1 - 2012/5

N2 - Removing dynamic objects from videos is an extremely challenging problem that even visual effects professionals often solve with time-consuming manual frame-by-frame editing. We propose a new approach to video completion that can deal with complex scenes containing dynamic background and non-periodical moving objects. We build upon the idea that the spatio-temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible. Video completion is performed by solving a large combinatorial problem that searches for an optimal pattern of pixel offsets from occluded to unoccluded regions. Our contribution includes an energy functional that generalizes well over different scenes with stable parameters, and that has the desirable convergence properties for a graph-cut-based optimization. We provide an interface to guide the completion process that both reduces computation time and allows for efficient correction of small errors in the result. We demonstrate that our approach can effectively complete complex, high-resolution occlusions that are greater in difficulty than what existing methods have shown.

AB - Removing dynamic objects from videos is an extremely challenging problem that even visual effects professionals often solve with time-consuming manual frame-by-frame editing. We propose a new approach to video completion that can deal with complex scenes containing dynamic background and non-periodical moving objects. We build upon the idea that the spatio-temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible. Video completion is performed by solving a large combinatorial problem that searches for an optimal pattern of pixel offsets from occluded to unoccluded regions. Our contribution includes an energy functional that generalizes well over different scenes with stable parameters, and that has the desirable convergence properties for a graph-cut-based optimization. We provide an interface to guide the completion process that both reduces computation time and allows for efficient correction of small errors in the result. We demonstrate that our approach can effectively complete complex, high-resolution occlusions that are greater in difficulty than what existing methods have shown.

U2 - 10.1111/j.1467-8659.2012.03000.x

DO - 10.1111/j.1467-8659.2012.03000.x

M3 - Journal article

VL - 31

SP - 219

EP - 228

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

IS - 2 Pt 1

ER -