Parallel and deterministic algorithms from MRF's

Surface reconstruction

Davi Geiger, Federico Girosi

Research output: Contribution to journalArticle

Abstract

Deterministic approximations to Markov random field models are derived. One of the models is shown to give in a natural way the graduated nonconvexity (GNC) algorithm proposed by A. Blake and A. Zisserman (1987). 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 statistical 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
Volume13
Issue number5
DOIs
StatePublished - May 1991

Fingerprint

Surface Reconstruction
Surface reconstruction
Deterministic Algorithm
Parallel Algorithms
Non-convexity
Statistical mechanics
Model
Statistical Mechanics
Mean Field
Random Field
Iterative Algorithm
Discontinuity
Approximation
Experiment
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Parallel and deterministic algorithms from MRF's : Surface reconstruction. / Geiger, Davi; Girosi, Federico.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 5, 05.1991, p. 401-412.

Research output: Contribution to journalArticle

@article{e5edc0e5da334669a23e70fe3c0e820d,
title = "Parallel and deterministic algorithms from MRF's: Surface reconstruction",
abstract = "Deterministic approximations to Markov random field models are derived. One of the models is shown to give in a natural way the graduated nonconvexity (GNC) algorithm proposed by A. Blake and A. Zisserman (1987). 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 statistical 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.",
author = "Davi Geiger and Federico Girosi",
year = "1991",
month = "5",
doi = "10.1109/34.134040",
language = "English (US)",
volume = "13",
pages = "401--412",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Parallel and deterministic algorithms from MRF's

T2 - Surface reconstruction

AU - Geiger, Davi

AU - Girosi, Federico

PY - 1991/5

Y1 - 1991/5

N2 - Deterministic approximations to Markov random field models are derived. One of the models is shown to give in a natural way the graduated nonconvexity (GNC) algorithm proposed by A. Blake and A. Zisserman (1987). 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 statistical 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.

AB - Deterministic approximations to Markov random field models are derived. One of the models is shown to give in a natural way the graduated nonconvexity (GNC) algorithm proposed by A. Blake and A. Zisserman (1987). 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 statistical 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.

UR - http://www.scopus.com/inward/record.url?scp=0026151642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026151642&partnerID=8YFLogxK

U2 - 10.1109/34.134040

DO - 10.1109/34.134040

M3 - Article

VL - 13

SP - 401

EP - 412

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

ER -