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

Shape from texture.

J Aloimonos1

  • 1Computer Vision Laboratory, University of Maryland, College Park 20742.

Biological Cybernetics
|January 1, 1988
PubMed
Summary
This summary is machine-generated.

Recovering 3D surface structure from images is key to visual perception. This study shows that analyzing texture distortion or image edges can reveal surface shape and orientation from single images.

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

Motion-boundary illusions and their regularization.

Proceedings. Biological sciences·1990
Same author

On the kinetic depth effect.

Biological cybernetics·1989
Same author

Finding motion parameters from spherical motion fields (or the advantages of having eyes in the back of your head).

Biological cybernetics·1988
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Geometry

Background:

  • Recovering 3D surface structure is a fundamental problem in visual perception.
  • Texture geometry in images provides crucial information about 3D shape due to projective distortion.

Purpose of the Study:

  • To investigate methods for recovering 3D surface structure from monocular (single-lens) image views.
  • To analyze how texture and contour information can be used to infer surface shape and orientation.

Main Methods:

  • Analyzing the projective distortion of natural textures under perspective projection.
  • Utilizing the uniform density assumption of texels (texture elements).
  • Employing image contour lengths as an alternative cue when texels are not discernible.

Related Experiment Videos

Main Results:

  • The uniform density assumption for texels is sufficient to recover the orientation of a single textured plane.
  • Image edges and contour lengths can determine shape under a more general assumption about world plane contours.
  • Experimental results validate the methods for both synthetic and natural images.

Conclusions:

  • Texture distortion analysis is a viable method for 3D surface structure recovery in computer vision.
  • Image contour properties offer a robust alternative for shape determination when texture is sparse or absent.