Video inpainting algorithm using Spatio-temporal consistency

Sang Heon Lee; Soon Young Lee; Jun Hee Heu; Chang-Su Kim; Sang Uk Lee

doi:10.1117/12.805892

Video inpainting algorithm using Spatio-temporal consistency

Sang Heon Lee, Soon Young Lee, Jun Hee Heu, Chang-Su Kim, Sang Uk Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7246
DOIs	https://doi.org/10.1117/12.805892
Publication status	Published - 2009
Event	Computational Imaging VII - San Jose, CA, United States Duration: 2009 Jan 19 → 2009 Jan 20

Other

Other	Computational Imaging VII
Country/Territory	United States
City	San Jose, CA
Period	09/1/19 → 09/1/20

Keywords

Inpainting
Optimization
Restoration
Spatio-temporal inpainting
Video editing

ASJC Scopus subject areas

Applied Mathematics
Computer Science Applications
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Condensed Matter Physics

Access to Document

10.1117/12.805892

Cite this

@inproceedings{b98434fdfb6249ff9f2fdbef38737e12,

title = "Video inpainting algorithm using Spatio-temporal consistency",

abstract = "A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.",

keywords = "Inpainting, Optimization, Restoration, Spatio-temporal inpainting, Video editing",

author = "Lee, {Sang Heon} and Lee, {Soon Young} and Heu, {Jun Hee} and Chang-Su Kim and Lee, {Sang Uk}",

year = "2009",

doi = "10.1117/12.805892",

language = "English",

volume = "7246",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Computational Imaging VII ; Conference date: 19-01-2009 Through 20-01-2009",

}

TY - GEN

T1 - Video inpainting algorithm using Spatio-temporal consistency

AU - Lee, Sang Heon

AU - Lee, Soon Young

AU - Heu, Jun Hee

AU - Kim, Chang-Su

AU - Lee, Sang Uk

PY - 2009

Y1 - 2009

N2 - A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.

AB - A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.

KW - Inpainting

KW - Optimization

KW - Restoration

KW - Spatio-temporal inpainting

KW - Video editing

UR - http://www.scopus.com/inward/record.url?scp=65649125657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65649125657&partnerID=8YFLogxK

U2 - 10.1117/12.805892

DO - 10.1117/12.805892

M3 - Conference contribution

AN - SCOPUS:65649125657

VL - 7246

BT - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Computational Imaging VII

Y2 - 19 January 2009 through 20 January 2009

ER -

Video inpainting algorithm using Spatio-temporal consistency

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this