Image completion using structural priority belief propagation

Yingzhen Yang, Yin Zhu, Qunsheng Peng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 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 languageEnglish (US)
Title of host publicationMM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums
Pages717-720
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums - Beijing, China
Duration: Oct 19 2009Oct 24 2009

Publication series

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

Other

Other17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums
CountryChina
CityBeijing
Period10/19/0910/24/09

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

Fingerprint Dive into the research topics of 'Image completion using structural priority belief propagation'. Together they form a unique fingerprint.

Cite this