Parallel and Deterministic Algorithms from MRF’s: Surface Reconstruction

Davi Geiger, Federico Girosi

Research output: Contribution to journalArticlepeer-review


In recent years many researchers have investigated the use of Bayesian and the special case of Markov random fields (MRF’s) for computer vision. They can be applied for example to reconstruct surfaces from sparse and noisy depth data coming from the output of a visual process, or to integrate early vision processes to label physical discontinuities. Drawbacks of MRF models are the computational complexity of the implementation and the difficulty in estimating the parameters of the model. In this paper we derive deterministic approximations to MRI models. One of the models is shown to give in a natural way the graduated nonconvexity (GNC) algorithm proposed by Blake and Zisserman. This model can be applied to smooth a field preserving its discontinuities. A class of more complex models is then proposed in order to deal with a variety of vision problems. All the theoretical results are obtained in the framework of sta-tistical mechanics and mean field techniques. A parallel, iterative algorithm to solve the deterministic equations of the two models is presented, together with some experiments on synthetic and real images.

Original languageEnglish (US)
Pages (from-to)401-412
Number of pages12
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number5
StatePublished - May 1991


  • Bayes’ theory
  • Markov random fields
  • image enhancement
  • image segmentation
  • integration
  • mean field techniques
  • mean field theory
  • parallel algorithms
  • surface reconstruc-tion

ASJC Scopus subject areas

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


Dive into the research topics of 'Parallel and Deterministic Algorithms from MRF’s: Surface Reconstruction'. Together they form a unique fingerprint.

Cite this