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 Concept Videos

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
Modeling and Similitude01:12

Modeling and Similitude

Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...

You might also read

Related Articles

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

Sort by
Same author

Why You Cannot Rank First: Modifications for Benchmarking Six-Degree-of-Freedom Visual Localization Algorithms.

Sensors (Basel, Switzerland)·2023
Same author

Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

An Iterative Co-Training Transductive Framework for Zero Shot Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN).

Frontiers in computational neuroscience·2020
Same author

Robust Camera Translation Estimation via Rank Enforcement.

IEEE transactions on cybernetics·2020
Same author

Detail Preserved Surface Reconstruction from Point Cloud.

Sensors (Basel, Switzerland)·2019

Related Experiment Video

Updated: Jun 13, 2026

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

Modeling stereopsis via Markov random field.

Yansheng Ming1, Zhanyi Hu

  • 1National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, PRC. ysming@nlpr.ia.ac.cn

Neural Computation
|May 5, 2010
PubMed
Summary
This summary is machine-generated.

This study proposes a biologically plausible Markov random field (MRF) model for stereo vision. The model accurately explains human depth perception and improves upon existing methods for stereo matching.

More Related Videos

Stereoacuity Improvement using Random-Dot Video Games
06:25

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Related Experiment Videos

Last Updated: Jun 13, 2026

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

Stereoacuity Improvement using Random-Dot Video Games
06:25

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Psychophysics

Background:

  • Markov random fields (MRFs) and belief propagation are key to high-performance stereo vision algorithms.
  • The biological plausibility of these computational models remains an active area of research.

Purpose of the Study:

  • To design a biologically constrained Markov random field (MRF) model for stereo vision.
  • To investigate the physiological and psychophysical basis of MRF-based stereo vision algorithms.

Main Methods:

  • Developed an MRF model incorporating physiological (disparity energy model) and psychophysical (stimulus separation effects) constraints.
  • Tested the model on repetitive patterns, random dot stereograms, and natural scene images.
  • Compared model performance against a coarse-to-fine model.

Main Results:

  • The model successfully explains human depth perception in images with repetitive patterns, previously attributed to second-order mechanisms.
  • False matches from the disparity energy model were effectively removed in simulations.
  • The model demonstrated superior performance in computing absolute disparity for small objects with larger relative disparities compared to the coarse-to-fine model.

Conclusions:

  • Stereopsis can be implemented by neural networks that resemble MRFs.
  • The proposed model aligns with physiological findings, suggesting neurons selective for absolute disparity with facilitative extra receptive fields are crucial.
  • The MRF framework offers a biologically plausible approach to understanding stereo vision.