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.
Vision01:24

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by
Same author

High-Quality Entity Segmentation and Grounding.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Editing 3D Scenes via Text Prompts Without Retraining.

IEEE transactions on visualization and computer graphics·2026
Same author

DrivingGaussian++: Toward Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency.

IEEE transactions on pattern analysis and machine intelligence·2025

Related Experiment Video

Updated: Jun 6, 2026

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Higher-Dimensional Affine Registration and Vision Applications.

S M Shahed Nejhum, Yu-Tseh Chi, Jeffrey Ho

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 8, 2010
    PubMed
    Summary

    This study introduces a novel algorithm for high-dimensional affine registration, enabling accurate point-set matching in dimensions beyond three for complex computer vision tasks.

    Related Experiment Videos

    Last Updated: Jun 6, 2026

    Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
    05:05

    Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

    Published on: November 23, 2019

    Area of Science:

    • Computer Vision
    • Computational Geometry
    • Applied Mathematics

    Background:

    • Affine registration is well-established in 2D and 3D.
    • Existing methods struggle with higher dimensions (4-12) due to inefficiency.
    • Novel applications require registration in R(m), m > 3.

    Purpose of the Study:

    • Develop an efficient algorithm for affine registration in R(m), m > 3.
    • Address limitations of current methods in high-dimensional spaces.
    • Solve novel matching problems like stereo correspondence under motion and image set matching.

    Main Methods:

    • Iterative estimation of correspondences and affine transform.
    • Novel local spectral features derived from distance matrices for initial correspondence.
    • Algorithm handles point sets of varying sizes.
    • Robustness to noise and outliers via local features.

    Main Results:

    • Successfully registered synthetic point sets in various high dimensions.
    • Demonstrated effectiveness on problems including stereo correspondence, image set matching, and covariant point-set matching.
    • Algorithm shows robustness against deformation and noise.

    Conclusions:

    • The proposed algorithm effectively performs affine registration in R(m) for m = 4-12.
    • It overcomes the limitations of existing methods in higher dimensions.
    • The approach is suitable for challenging computer vision applications requiring high-dimensional matching.