Image completion using structural priority belief propagation

Yingzhen Yang; Yin Zhu; Qunsheng Peng

doi:10.1145/1631272.1631396

Image completion using structural priority belief propagation

Yingzhen Yang, Yin Zhu, Qunsheng Peng

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

11 Scopus citations

Abstract

A new image completion algorithm called Structural Priority Belief Propagation (SPBP) is presented to deal with LDV based image completion in this paper. LDV completion is a new form of image completion based on another large displacement view (LDV) of the same scene, no wonder, it has the potential of repairing large unknown region with salient structure information. In order to complete such unknown region, SPBP makes two important extensions over existing Priority-BP: dynamic weight of structural consistency and structural priority inheritance so as to propagate linear structure with correct priority, meanwhile it promotes texture propagation adhering to a global optimization scheme. Experimental results demonstrate that SPBP can obtain more satisfactory results than other LDV completion algorithms and it also performs well for traditional single image completion.

Original language	English (US)
Title of host publication	MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums
Pages	717-720
Number of pages	4
DOIs	https://doi.org/10.1145/1631272.1631396
State	Published - 2009
Externally published	Yes
Event	17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums - Beijing, China Duration: Oct 19 2009 → Oct 24 2009

Publication series

Name	MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums

Other

Other	17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums
Country/Territory	China
City	Beijing
Period	10/19/09 → 10/24/09

Keywords

Image completion
Large displacement view (LDV)
Structural Priority Belief Propagation (SPBP)

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/1631272.1631396

Cite this

Image completion using structural priority belief propagation. / Yang, Yingzhen; Zhu, Yin; Peng, Qunsheng.
MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. 2009. p. 717-720 (MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums).

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

Yang, Y, Zhu, Y & Peng, Q 2009, Image completion using structural priority belief propagation. in MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums, pp. 717-720, 17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums, Beijing, China, 10/19/09. https://doi.org/10.1145/1631272.1631396

@inproceedings{9ed53f5b38c14fd795514476c5b2a4b0,

title = "Image completion using structural priority belief propagation",

abstract = "A new image completion algorithm called Structural Priority Belief Propagation (SPBP) is presented to deal with LDV based image completion in this paper. LDV completion is a new form of image completion based on another large displacement view (LDV) of the same scene, no wonder, it has the potential of repairing large unknown region with salient structure information. In order to complete such unknown region, SPBP makes two important extensions over existing Priority-BP: dynamic weight of structural consistency and structural priority inheritance so as to propagate linear structure with correct priority, meanwhile it promotes texture propagation adhering to a global optimization scheme. Experimental results demonstrate that SPBP can obtain more satisfactory results than other LDV completion algorithms and it also performs well for traditional single image completion.",

keywords = "Image completion, Large displacement view (LDV), Structural Priority Belief Propagation (SPBP)",

author = "Yingzhen Yang and Yin Zhu and Qunsheng Peng",

note = "Copyright: Copyright 2010 Elsevier B.V., All rights reserved.; 17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums ; Conference date: 19-10-2009 Through 24-10-2009",

year = "2009",

doi = "10.1145/1631272.1631396",

language = "English (US)",

isbn = "9781605586083",

series = "MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums",

pages = "717--720",

booktitle = "MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums",

}

TY - GEN

T1 - Image completion using structural priority belief propagation

AU - Yang, Yingzhen

AU - Zhu, Yin

AU - Peng, Qunsheng

PY - 2009

Y1 - 2009

N2 - A new image completion algorithm called Structural Priority Belief Propagation (SPBP) is presented to deal with LDV based image completion in this paper. LDV completion is a new form of image completion based on another large displacement view (LDV) of the same scene, no wonder, it has the potential of repairing large unknown region with salient structure information. In order to complete such unknown region, SPBP makes two important extensions over existing Priority-BP: dynamic weight of structural consistency and structural priority inheritance so as to propagate linear structure with correct priority, meanwhile it promotes texture propagation adhering to a global optimization scheme. Experimental results demonstrate that SPBP can obtain more satisfactory results than other LDV completion algorithms and it also performs well for traditional single image completion.

AB - A new image completion algorithm called Structural Priority Belief Propagation (SPBP) is presented to deal with LDV based image completion in this paper. LDV completion is a new form of image completion based on another large displacement view (LDV) of the same scene, no wonder, it has the potential of repairing large unknown region with salient structure information. In order to complete such unknown region, SPBP makes two important extensions over existing Priority-BP: dynamic weight of structural consistency and structural priority inheritance so as to propagate linear structure with correct priority, meanwhile it promotes texture propagation adhering to a global optimization scheme. Experimental results demonstrate that SPBP can obtain more satisfactory results than other LDV completion algorithms and it also performs well for traditional single image completion.

KW - Image completion

KW - Large displacement view (LDV)

KW - Structural Priority Belief Propagation (SPBP)

UR - http://www.scopus.com/inward/record.url?scp=72449202039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449202039&partnerID=8YFLogxK

U2 - 10.1145/1631272.1631396

DO - 10.1145/1631272.1631396

M3 - Conference contribution

AN - SCOPUS:72449202039

SN - 9781605586083

T3 - MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums

SP - 717

EP - 720

BT - MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums

T2 - 17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums

Y2 - 19 October 2009 through 24 October 2009

ER -

Image completion using structural priority belief propagation

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this