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

Symmetric 3D objects are an easy case for 2D object recognition

T Vetter1, T Poggio

  • 1Max-Planck-Institut für Biologische Kybernetik, Tübingen, Germany.

Spatial Vision
|January 1, 1994
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

Correction: Excess of NPM-ALK oncogenic signaling promotes cellular apoptosis and drug dependency.

Oncogene·2025
Same author

An analysis of training and generalization errors in shallow and deep networks.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Missing facial parts computed by a morphable model and transferred directly to a polyamide laser-sintered prosthesis: an innovation study.

The British journal of oral & maxillofacial surgery·2011
Same author

Response from sinha and poggio.

Trends in cognitive sciences·2011
Same author

[Mucopolysaccharidoses].

Der Orthopade·2008
Same author

[Hyperphosphatasia and hypophosphatasia in childhood].

Der Orthopade·2007
Same journal

Comment on 'angle illusion on a picture's surface' by Hammad et al. (2008).

Spatial vision·2009
Same journal

Feature-based attentional modulation increases with stimulus separation in divided-attention tasks.

Spatial vision·2009
Same journal

Spatial distance between target and irrelevant patch modulates detection in a texture segmentation task.

Spatial vision·2009
Same journal

Inhibition related impairments of coherent motion perception in the attention-induced motion blindness paradigm.

Spatial vision·2009
Same journal

Recognition units in reading: backward masking experiments.

Spatial vision·2009
Same journal

Spatial-temporal modeling of interactive image interpretation.

Spatial vision·2009
See all related articles

Object recognition from a single 2D view is possible for symmetric 3D objects. Exploiting symmetry allows generating virtual views, reducing the need for multiple model views in computer vision.

Area of Science:

  • Computer Vision
  • Computational Geometry
  • Robotics

Background:

  • The 1.5-views theorem states that recognizing a 3D object from a novel 2D view requires at least two 2D model views for orthographic projection.
  • Current methods often necessitate multiple 2D views for accurate 3D object recognition.

Purpose of the Study:

  • To investigate if object recognition can be achieved from a single 2D model view by leveraging prior knowledge of object symmetry.
  • To determine the sufficiency of exploiting symmetry for 3D object recognition.

Main Methods:

  • Utilizing the properties of bilateral symmetry in 3D objects to generate 'virtual' views from a single 2D model view.
  • Analyzing point correspondences between views to establish object recognition criteria.

Related Experiment Videos

Main Results:

  • It is proven that one non-accidental 2D model view is sufficient for recognizing any bilaterally symmetric 3D object.
  • For bilaterally symmetric objects, the correspondence of four points between two views uniquely determines the correspondence of all other points.
  • Higher-order symmetries enable the recovery of Euclidean structure from a single 2D view.

Conclusions:

  • Exploiting object symmetry significantly reduces the number of required 2D model views for 3D object recognition.
  • Symmetry provides a powerful mechanism for enhancing the efficiency and feasibility of single-view 3D object recognition.