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

Depth estimation and image restoration using defocused stereo pairs.

A N Rajagopalan1, S Chaudhuri, Uma Mudenagudi

  • 1Department of Electrical Engineering, Indian Institute of Technology, Chennai 600 036, India. raju@ee.iitm.ernet.in

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 4, 2004
PubMed
Summary

This study introduces a novel method for depth estimation using real aperture camera images by combining defocus and stereo visual cues. This approach enhances depth accuracy compared to using either cue alone.

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

Development and validation of a CNN model for grading oral epithelial dysplasia.

Revista espanola de patologia : publicacion oficial de la Sociedad Espanola de Anatomia Patologica y de la Sociedad Espanola de Citologia·2026
Same author

QuPath for automated analysis of digital images of oral epithelial dysplasia.

Journal of oral and maxillofacial pathology : JOMFP·2024
Same author

A Multiscale Inelastic Internal State Variable Corrosion Model.

Materials (Basel, Switzerland)·2024
Same author

Can a shock-induced phonon up-pumping model relate to impact sensitivity of molecular crystals, polymorphs and cocrystals?

RSC advances·2022
Same author

A flexible-molecule force field to model and study hexanitrohexaazaisowurtzitane (CL-20) - polymorphism under extreme conditions.

RSC advances·2022
Same author

Improved predictions of thermomechanical properties of molecular crystals from energy and dispersion corrected DFT.

The Journal of chemical physics·2021

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Photography

Background:

  • Depth estimation is crucial for 3D scene understanding and robotics.
  • Existing methods like stereo vision and defocus-based depth estimation have limitations.
  • Real aperture cameras offer unique defocus properties that can be leveraged.

Purpose of the Study:

  • To develop a robust depth estimation method by fusing defocus and stereo cues from real aperture camera images.
  • To improve depth map accuracy beyond what stereo or defocus cues provide individually.
  • To achieve simultaneous depth recovery and space-variant image restoration.

Main Methods:

  • Modeling depth maps and original images as Markov Random Fields (MRFs) with smoothness priors.
  • Utilizing stereo-based constraints in conjunction with defocus information.

Related Experiment Videos

  • Employing simulated annealing to minimize a defined energy function for parameter estimation.

    • Main Results:

    • Achieved improved depth estimation by integrating stereo and defocus cues.
    • Demonstrated simultaneous recovery of scene depth and restoration of the focused image.
    • The proposed method offers enhanced accuracy despite higher computational cost compared to standard stereo or DFD methods.

    Conclusions:

    • Fusing defocus and stereo cues provides a more accurate depth estimation than individual methods.
    • The MRF framework with simulated annealing is effective for joint depth and image restoration.
    • This technique enables simultaneous depth mapping and deblurring for real aperture camera imagery.