Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A Bayesian approach to the stereo correspondence problem.

Jenny C A Read1

  • 1University Laboratory of Physiology, Oxford, OX1 3PT, UK. jenny.read@physiol.ox.ac.uk

Neural Computation
|May 22, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Gaze Error Estimation and Linear Transformation to Improve Accuracy of Video-Based Eye Trackers.

Vision (Basel, Switzerland)·2025
Same author

Effect of alcohol on the speed of shifting endogenous and exogenous attention.

Experimental and clinical psychopharmacology·2025
Same author

Eye posture and screen alignment with simulated see-through head-mounted displays.

Journal of vision·2025
Same author

Physically stressed bees expect less reward in an active choice judgement bias test.

Proceedings. Biological sciences·2024
Same author

Focusing on mixed narrow band stimuli: Implications for mechanisms of accommodation and displays.

Journal of vision·2024
Same author

Different memory systems in food-hoarding birds: A response to Pravosudov.

Learning & behavior·2024
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces a probabilistic stereo correspondence method. It considers all potential matches simultaneously, assigning probabilities to solve complex visual challenges like occlusion.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Psychophysics

Background:

  • The stereo correspondence problem is fundamental to 3D vision.
  • Traditional methods seek unique matches, failing with occlusions (e.g., Panum's limiting case).
  • Existing psychophysical data provides a basis for modeling visual perception.

Purpose of the Study:

  • To develop a probabilistic approach for stereo correspondence.
  • To address limitations of unique-match methods in complex visual scenes.
  • To integrate psychophysical constraints into a computational model.

Main Methods:

  • A probabilistic framework considers all possible retinal matches simultaneously.
  • Each potential match is assigned a probability of correctness.

Related Experiment Videos

  • Bayesian analysis, based on prior psychophysical data, informs match probabilities and incorporates constraints.

    • Main Results:

    • The model handles scenarios with occlusions, where unique matches are ill-defined.
    • Probabilistic assignments provide a more robust solution than deterministic methods.
    • The approach is suitable for a range of visual stimuli.

    Conclusions:

    • A probabilistic, Bayesian approach offers a powerful solution to the stereo correspondence problem.
    • This method effectively models visual perception in the presence of occlusion.
    • The model demonstrates plausible behavior across diverse visual scenarios.