The joy of sampling

D. A. Forsyth, J. Haddon, S. Ioffe

Research output: Contribution to journalArticle

Abstract

A standard method for handling Bayesian models is to use Markov chain Monte Carlo methods to draw samples from the posterior. We demonstrate this method on two core problems in computer vision-structure from motion and colour constancy. These examples illustrate a samplers producing useful representations for very large problems. We demonstrate that the sampled representations are trustworthy, using consistency checks in the experimental design. The sampling solution to structure from motion is strictly better than the factorisation approach, because: it reports uncertainty on structure and position measurements in a direct way; it can identify tracking errors; and its estimates of covariance in marginal point position are reliable. Our colour constancy solution is strictly better than competing approaches, because: it reports uncertainty on surface colour and illuminant measurements in a direct way; it incorporates all available constraints on surface reflectance and on illumination in a direct way; and it integrates a spatial model of reflectance and illumination distribution with a rendering model in a natural way. One advantage of a sampled representation is that it can be resampled to take into account other information. We demonstrate the effect of knowing that, in our colour constancy example, a surface viewed in two different images is in fact the same object. We conclude with a general discussion of the strengths and weaknesses of the sampling paradigm as a tool for computer vision.

Original languageEnglish (US)
Pages (from-to)109-134
Number of pages26
JournalInternational Journal of Computer Vision
Volume41
Issue number1-2
DOIs
StatePublished - Jan 1 2001
Externally publishedYes

Fingerprint

Sampling
Color
Computer vision
Lighting
Position measurement
Factorization
Design of experiments
Markov processes
Monte Carlo methods
Uncertainty

Keywords

  • Colour constancy
  • Markov chain Monte Carlo
  • Structure from motion

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

The joy of sampling. / Forsyth, D. A.; Haddon, J.; Ioffe, S.

In: International Journal of Computer Vision, Vol. 41, No. 1-2, 01.01.2001, p. 109-134.

Research output: Contribution to journalArticle

Forsyth, D. A. ; Haddon, J. ; Ioffe, S. / The joy of sampling. In: International Journal of Computer Vision. 2001 ; Vol. 41, No. 1-2. pp. 109-134.
@article{ede53777401b49d592e1b556ac2faab6,
title = "The joy of sampling",
abstract = "A standard method for handling Bayesian models is to use Markov chain Monte Carlo methods to draw samples from the posterior. We demonstrate this method on two core problems in computer vision-structure from motion and colour constancy. These examples illustrate a samplers producing useful representations for very large problems. We demonstrate that the sampled representations are trustworthy, using consistency checks in the experimental design. The sampling solution to structure from motion is strictly better than the factorisation approach, because: it reports uncertainty on structure and position measurements in a direct way; it can identify tracking errors; and its estimates of covariance in marginal point position are reliable. Our colour constancy solution is strictly better than competing approaches, because: it reports uncertainty on surface colour and illuminant measurements in a direct way; it incorporates all available constraints on surface reflectance and on illumination in a direct way; and it integrates a spatial model of reflectance and illumination distribution with a rendering model in a natural way. One advantage of a sampled representation is that it can be resampled to take into account other information. We demonstrate the effect of knowing that, in our colour constancy example, a surface viewed in two different images is in fact the same object. We conclude with a general discussion of the strengths and weaknesses of the sampling paradigm as a tool for computer vision.",
keywords = "Colour constancy, Markov chain Monte Carlo, Structure from motion",
author = "Forsyth, {D. A.} and J. Haddon and S. Ioffe",
year = "2001",
month = "1",
day = "1",
doi = "10.1023/A:1011165200654",
language = "English (US)",
volume = "41",
pages = "109--134",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1-2",

}

TY - JOUR

T1 - The joy of sampling

AU - Forsyth, D. A.

AU - Haddon, J.

AU - Ioffe, S.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - A standard method for handling Bayesian models is to use Markov chain Monte Carlo methods to draw samples from the posterior. We demonstrate this method on two core problems in computer vision-structure from motion and colour constancy. These examples illustrate a samplers producing useful representations for very large problems. We demonstrate that the sampled representations are trustworthy, using consistency checks in the experimental design. The sampling solution to structure from motion is strictly better than the factorisation approach, because: it reports uncertainty on structure and position measurements in a direct way; it can identify tracking errors; and its estimates of covariance in marginal point position are reliable. Our colour constancy solution is strictly better than competing approaches, because: it reports uncertainty on surface colour and illuminant measurements in a direct way; it incorporates all available constraints on surface reflectance and on illumination in a direct way; and it integrates a spatial model of reflectance and illumination distribution with a rendering model in a natural way. One advantage of a sampled representation is that it can be resampled to take into account other information. We demonstrate the effect of knowing that, in our colour constancy example, a surface viewed in two different images is in fact the same object. We conclude with a general discussion of the strengths and weaknesses of the sampling paradigm as a tool for computer vision.

AB - A standard method for handling Bayesian models is to use Markov chain Monte Carlo methods to draw samples from the posterior. We demonstrate this method on two core problems in computer vision-structure from motion and colour constancy. These examples illustrate a samplers producing useful representations for very large problems. We demonstrate that the sampled representations are trustworthy, using consistency checks in the experimental design. The sampling solution to structure from motion is strictly better than the factorisation approach, because: it reports uncertainty on structure and position measurements in a direct way; it can identify tracking errors; and its estimates of covariance in marginal point position are reliable. Our colour constancy solution is strictly better than competing approaches, because: it reports uncertainty on surface colour and illuminant measurements in a direct way; it incorporates all available constraints on surface reflectance and on illumination in a direct way; and it integrates a spatial model of reflectance and illumination distribution with a rendering model in a natural way. One advantage of a sampled representation is that it can be resampled to take into account other information. We demonstrate the effect of knowing that, in our colour constancy example, a surface viewed in two different images is in fact the same object. We conclude with a general discussion of the strengths and weaknesses of the sampling paradigm as a tool for computer vision.

KW - Colour constancy

KW - Markov chain Monte Carlo

KW - Structure from motion

UR - http://www.scopus.com/inward/record.url?scp=0034991078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034991078&partnerID=8YFLogxK

U2 - 10.1023/A:1011165200654

DO - 10.1023/A:1011165200654

M3 - Article

AN - SCOPUS:0034991078

VL - 41

SP - 109

EP - 134

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1-2

ER -