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

Example-based photometric stereo: shape reconstruction with general, varying BRDFs.

Aaron Hertzmann1, Steven M Seitz

  • 1Computer Science Department, University of Toronto, 10 King's College Road, Room 3302, Toronto, ON M5S 3G4 Canada. hertzman@dgp.toronto.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|August 27, 2005
PubMed
Summary

This study introduces a novel shape reconstruction technique that computes object geometry and material properties from images. It handles complex, varying materials and lighting without extensive calibration, simplifying 3D object analysis.

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

Lossy processing principles in 2D and 3D vision.

The Behavioral and brain sciences·2025
Same author

Don't look at the camera: Achieving perceived eye contact in remote video communication.

Journal of vision·2025
Same author

Viewers perceive shape in pictures according to per-fixation perspective.

Scientific reports·2025
Same author

Benchmark suites instead of leaderboards for evaluating AI fairness.

Patterns (New York, N.Y.)·2024
Same author

Toward a theory of perspective perception in pictures.

Journal of vision·2024
Same author

New Insights in Smooth Occluding Contours for Nonphotorealistic Rendering.

IEEE computer graphics and applications·2024

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Computational Imaging

Background:

  • Accurate 3D shape reconstruction from images is crucial for various applications.
  • Existing methods often struggle with objects exhibiting complex or spatially varying material properties (BRDFs).
  • Handling arbitrary and unknown lighting conditions remains a significant challenge in shape recovery.

Purpose of the Study:

  • To develop a robust technique for computing object geometry from images, accommodating general and spatially-varying reflectance properties.
  • To simultaneously segment surfaces into distinct material types.
  • To enable shape reconstruction under uncalibrated, arbitrary distant lighting environments.

Main Methods:

  • The technique utilizes a fixed camera viewpoint with varying illumination conditions.

Related Experiment Videos

  • It leverages example objects with known geometry and similar materials imaged under identical lighting.
  • The method computes object geometry and material segmentation without requiring extensive camera calibration.

    • Main Results:

    • The approach successfully reconstructs the geometry of objects with arbitrary and spatially-varying Bidirectional Reflectance Distribution Functions (BRDFs).
    • It provides a full segmentation of surfaces into different material types.
    • The method demonstrates robustness across diverse and unknown lighting environments.

    Conclusions:

    • This technique offers a simplified yet powerful approach to 3D shape and material property computation from images.
    • It overcomes limitations of previous methods by handling complex materials and uncalibrated lighting.
    • The minimal calibration requirement makes this method highly practical for real-world applications.