BC&GC-based dense stereo by belief propagation

Hongsheng Zhang, Shahriar Negahdaripour

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

Abstract

Belief propagation (BP) have emerged as powerful tools in the realm of dense stereo computation. However the underlying brightness constancy (BC) assumption of existing methods severely limit the range of their applications. Augmenting BC with gradient constancy (GC) assumption has lead to a more accurate algorithm for optical flow computation. In this paper, these constraints are utilized in the frameworks of BP to broaden the application of stereo vision for 3D reconstruction. Results from experiments with semi-synthetic and real data illustrate that an algorithm incorporating these models generally yields better estimates, where the BC assumption is violated.

Original languageEnglish (US)
Title of host publicationProceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06
Number of pages1
DOIs
StatePublished - Oct 10 2006
EventFourth IEEE International Conference on Computer Vision Systems, ICVS'06 - New York, NY, United States
Duration: Jan 4 2006Jan 7 2006

Publication series

NameProceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06
Volume2006

Other

OtherFourth IEEE International Conference on Computer Vision Systems, ICVS'06
CountryUnited States
CityNew York, NY
Period1/4/061/7/06

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'BC&GC-based dense stereo by belief propagation'. Together they form a unique fingerprint.

  • Cite this

    Zhang, H., & Negahdaripour, S. (2006). BC&GC-based dense stereo by belief propagation. In Proceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06 [1578702] (Proceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06; Vol. 2006). https://doi.org/10.1109/ICVS.2006.62