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

The KGBR viewpoint-lighting ambiguity.

Alan Yuille1, James M Coughlan, Scott Konishi

  • 1Smith-Kettlewell Eye Research Institute, 2318 Fillmore Street, San Francisco, California 94115, USA. yuille@stat.ucla.edu

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|January 25, 2003
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

Scaling 3D Compositional Models for Robust Classification and Pose Estimation.

Proceedings. IEEE International Conference on Computer Vision·2026
Same author

A comprehensive survey of AI agents in healthcare.

Journal of biomedical informatics·2026
Same author

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More.

Proceedings of machine learning research·2026
Same author

Hyperplasia Functions as a Link between Obesity and Cancer.

Cancer research·2026
Same author

Mamba-Reg: Vision Mamba Also Needs Registers.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2025
Same author

NavGraph: Enhancing Blind Travelers' Navigation Experience and Safety.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2025
Same journal

Multi-module collaborative optimization-driven fast speckle correlation imaging in variable environments.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Secrecy performance analysis of NOMA-UWOC systems over a vertically stratified WGG oceanic turbulence channel.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Backscattering of plane waves in a composite system containing a rough surface and anisotropic scatterers.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Aspherical surface construction methods based on extended Jacobi polynomials.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

OCT sidelobe suppression method based on dual-path phase sinusoidal modulation and minimum value fusion.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Optical design concepts using wavelength-selective diffractive optics to enable miniaturized multimodal endoscopic imaging across separated spectral ranges.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
See all related articles

Researchers identified a new viewpoint-lighting ambiguity, the KGBR, affecting 3D structure estimation from images with unknown camera and lighting conditions. This impacts computer vision and 3D reconstruction accuracy.

Area of Science:

  • Computer Vision
  • 3D Reconstruction
  • Computational Imaging

Background:

  • Estimating 3D object and scene structure from images is challenging when viewpoint and lighting are unknown.
  • Existing methods grapple with visual ambiguities inherent in such scenarios.
  • Photometric cues like shading and shadowing are crucial but complex to model.

Purpose of the Study:

  • To identify and characterize a novel ambiguity in 3D structure and albedo estimation.
  • To analyze the impact of unknown viewpoint and lighting on visual reconstruction.
  • To establish a theoretical framework for understanding these ambiguities.

Main Methods:

  • Developed a novel viewpoint-lighting ambiguity termed KGBR.
  • Utilized an affine camera model with orthographic projection.

Related Experiment Videos

  • Modeled photometric cues using Lambertian reflectance, including cast and attached shadows.
  • Incorporated multiple light sources, excluding interreflections.

    • Main Results:

    • The KGBR ambiguity was mathematically derived, linking 3D affine transformations of geometry and albedo.
    • Established a connection between the KGBR and existing affine shape ambiguities.
    • Demonstrated the relationship to the generalized bas-relief (GBR) ambiguity.

    Conclusions:

    • The KGBR represents a fundamental ambiguity in inferring 3D structure and appearance from images.
    • Understanding this ambiguity is crucial for improving the robustness of 3D reconstruction algorithms.
    • The findings provide a theoretical basis for addressing limitations in computer vision under unconstrained conditions.