Efficient object-based video inpainting

M. Vijay Venkatesh; Sen ching Samson Cheung; Jian Zhao

doi:10.1016/j.patrec.2008.03.011

Efficient object-based video inpainting

M. Vijay Venkatesh, Sen ching Samson Cheung, Jian Zhao

Research output: Contribution to journal › Article › peer-review

50 Scopus citations

Abstract

Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle these challenges, a computationally-efficient algorithm that separately inpaints foreground objects and background is proposed. Using Dynamic Programming, foreground objects are holistically inpainted with object templates that minimizes a sliding-window dissimilarity cost function. Static background are inpainted by adaptive background replacement and image inpainting.

Original language	English
Pages (from-to)	168-179
Number of pages	12
Journal	Pattern Recognition Letters
Volume	30
Issue number	2
DOIs	https://doi.org/10.1016/j.patrec.2008.03.011
State	Published - Jan 15 2009

Bibliographical note

Funding Information:
The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.

Funding

The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.

Funders	Funder number
U.S. Department of Justice	2004-IJ-CK-K055

Keywords

Background replacement
Dynamic programming
Object segmentation
Sliding window
Template matching
Video inpainting

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/j.patrec.2008.03.011

Cite this

@article{1e1936240d1b48bb843a1ed9e5b0c3ee,

title = "Efficient object-based video inpainting",

abstract = "Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle these challenges, a computationally-efficient algorithm that separately inpaints foreground objects and background is proposed. Using Dynamic Programming, foreground objects are holistically inpainted with object templates that minimizes a sliding-window dissimilarity cost function. Static background are inpainted by adaptive background replacement and image inpainting.",

keywords = "Background replacement, Dynamic programming, Object segmentation, Sliding window, Template matching, Video inpainting",

author = "{Vijay Venkatesh}, M. and Cheung, {Sen ching Samson} and Jian Zhao",

note = "Funding Information: The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055. ",

year = "2009",

month = jan,

day = "15",

doi = "10.1016/j.patrec.2008.03.011",

language = "English",

volume = "30",

pages = "168--179",

number = "2",

}

TY - JOUR

T1 - Efficient object-based video inpainting

AU - Vijay Venkatesh, M.

AU - Cheung, Sen ching Samson

AU - Zhao, Jian

N1 - Funding Information: The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.

PY - 2009/1/15

Y1 - 2009/1/15

N2 - Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle these challenges, a computationally-efficient algorithm that separately inpaints foreground objects and background is proposed. Using Dynamic Programming, foreground objects are holistically inpainted with object templates that minimizes a sliding-window dissimilarity cost function. Static background are inpainted by adaptive background replacement and image inpainting.

AB - Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle these challenges, a computationally-efficient algorithm that separately inpaints foreground objects and background is proposed. Using Dynamic Programming, foreground objects are holistically inpainted with object templates that minimizes a sliding-window dissimilarity cost function. Static background are inpainted by adaptive background replacement and image inpainting.

KW - Background replacement

KW - Dynamic programming

KW - Object segmentation

KW - Sliding window

KW - Template matching

KW - Video inpainting

UR - http://www.scopus.com/inward/record.url?scp=56049112821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56049112821&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2008.03.011

DO - 10.1016/j.patrec.2008.03.011

M3 - Article

AN - SCOPUS:56049112821

SN - 0167-8655

VL - 30

SP - 168

EP - 179

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 2

ER -

Efficient object-based video inpainting

Abstract

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this