Journal Article
@Article
Artikel in Fachzeitschrift


Show entries of:

this year (2018) | last year (2017) | two years ago (2016) | Notes URL

Action:

login to update

Options:








Author, Editor(s)

Author(s):

Granados, Miguel
Tompkin, James
Kim, Kwang In
Grau, Oliver
Kautz, Jan
Theobalt, Christian

dblp
dblp
dblp
dblp
dblp
dblp

Not MPG Author(s):

Tompkin, James
Grau, Oliver
Kautz, Jan

BibTeX cite key*:

granados2012a

Title

Title*:

How Not to Be Seen - Object Removal from Videos of Crowded Scenes


granados12_vidinp.pdf (9794.93 KB)

Journal

Journal Title*:

Computer Graphics Forum (Proc. of EUROGRAPHICS)

Journal's URL:

http://www.wiley.com/bw/journal.asp?ref=0167-7055

Download URL
for the article:


Language:

English

Publisher

Publisher's
Name:

Wiley-Blackwell

Publisher's URL:

http://eu.wiley.com/WileyCDA/Section/index.html

Publisher's
Address:

Hoboken

ISSN:

0167-7055

Vol, No, pp, Date

Volume*:

31

Number:

2

Publishing Date:

July 2012

Pages*:

219-228

Number of
VG Pages:


Page Start:

219

Page End:

228

Sequence Number:


DOI:

10.1111/j.1467-8659.2012.03000.x

Note, Abstract, ©

Note:


(LaTeX) 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.

URL for the Abstract:


Categories,
Keywords:


HyperLinks / References / URLs:


Copyright Message:


Personal Comments:


Download
Access Level:

Public

Correlation

MPG Unit:

Max-Planck-Institut für Informatik



MPG Subunit:

Computer Graphics Group

Appearance:

MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort


BibTeX Entry:

@ARTICLE{granados2012a,
AUTHOR = {Granados, Miguel and Tompkin, James and Kim, Kwang In and Grau, Oliver and Kautz, Jan and Theobalt, Christian},
TITLE = {How Not to Be Seen - Object Removal from Videos of Crowded Scenes},
JOURNAL = {Computer Graphics Forum (Proc. of EUROGRAPHICS)},
PUBLISHER = {Wiley-Blackwell},
YEAR = {2012},
NUMBER = {2},
VOLUME = {31},
PAGES = {219--228},
ADDRESS = {Hoboken},
MONTH = {July},
ISBN = {0167-7055},
DOI = {10.1111/j.1467-8659.2012.03000.x},
}


Entry last modified by Anja Becker, 04/03/2013
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
Miguel Andrés Granados Velásquez
Created
12/20/2011 03:46:04 PM
Revisions
11.
10.
9.
8.
7.
Editor(s)
Anja Becker
Oliver Klehm
Christian Theobalt
Christian Theobalt
Christian Theobalt
Edit Dates
03.04.2013 15:34:03
02/12/2013 05:52:19 PM
01/04/2013 10:16:24 AM
01/04/2013 10:15:16 AM
01/04/2013 10:14:25 AM
Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section

View attachments here:


File Attachment Icon
granados12_vidinp.pdf