Spatial-temporal fusion for high accuracy depth maps using dynamic MRFs

Jiejie Zhu, Liang Wang, Jizhou Gao, Ruigang Yang

Research output: Contribution to journalArticlepeer-review

107 Scopus citations


Time-of-flight range sensors and passive stereo have complimentary characteristics in nature. To fuse them to get high accuracy depth maps varying over time, we extend traditional spatial MRFs to dynamic MRFs with temporal coherence. This new model allows both the spatial and the temporal relationship to be propagated in local neighbors. By efficiently finding a maximum of the posterior probability using Loopy Belief Propagation, we show that our approach leads to improved accuracy and robustness of depth estimates for dynamic scenes.

Original languageEnglish
Article number4815256
Pages (from-to)899-909
Number of pages11
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number5
StatePublished - 2010

Bibliographical note

Funding Information:
This work is supported in part by the University of Kentucky Research Foundation, the US Department of Homeland Security, US National Science Foundation Grants HCC-0448185 and CPA-0811647, and the Open Project Program of the State Key Lab of CAD&CG (grant no.: A0812), Zhejiang University, China. This work was performed while Jiejie Zhu was with the University of Kentucky.


  • Data fusion
  • Global optimization
  • MRFs
  • Stereo
  • Time-of-flight sensor

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Spatial-temporal fusion for high accuracy depth maps using dynamic MRFs'. Together they form a unique fingerprint.

Cite this