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

A network that learns to recognize three-dimensional objects.

T Poggio1, S Edelman

  • 1Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge 02139.

Nature
|January 18, 1990
PubMed
Summary
This summary is machine-generated.

This study introduces a novel computational vision scheme that learns 3-D object models from limited views. This approach enables robust visual recognition of objects from any viewpoint, overcoming challenges of illumination and pose variations.

Related Experiment Videos

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

Challenges faced by physicians when discussing the Type 2 diabetes diagnosis with patients: insights from a cross-national study (IntroDia<sup>®</sup> ).

Diabetic medicine : a journal of the British Diabetic Association·2017
Same author

Oxytocin receptor and vasopressin receptor 1a genes are respectively associated with emotional and cognitive empathy.

Hormones and behavior·2014
Same author

Control of type 2 diabetes after 1 year of laparoscopic adjustable gastric banding in the helping evaluate reduction in obesity (HERO) study.

Diabetes, obesity & metabolism·2014
Same author

Frailty and osteoporosis in older women--a prospective study.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2013
Same journal

Incoming US science academy chief vows to 'double down' on research.

Nature·2026
Same journal

Author Correction: Synthesis of enantioenriched atropisomers by biocatalytic deracemization.

Nature·2026
Same journal

Electrodeposited self-assembled molecules for perovskite photovoltaics.

Nature·2026
Same journal

Neutrino's nursery found: the 'Shadow Blaster'.

Nature·2026
Same journal

Dementia risk in middle-aged people linked to a blood protein.

Nature·2026
Same journal

Daily briefing: What's really happening with trust in science.

Nature·2026
See all related articles

Area of Science:

  • Computer Vision
  • Machine Learning
  • 3-D Object Recognition

Background:

  • Visual recognition of 3-D objects faces challenges with variable illumination and unknown object pose.
  • Existing methods often rely on 3-D models, but their automatic learning is difficult.
  • Intensity edges are more stable than raw intensity images under varying illumination.

Purpose of the Study:

  • To develop a computational vision scheme for automatic learning of 3-D object models.
  • To enable robust 3-D object recognition from any viewpoint.
  • To address the limitations of existing object recognition methods.

Main Methods:

  • A novel scheme based on the theory of approximation of multivariate functions was developed.
  • The scheme learns a function mapping any viewpoint to a standard view from a small set of perspective views.
  • A neural network equivalent to this scheme was implemented.

Main Results:

  • The developed scheme successfully learns to map viewpoints to a standard view.
  • The equivalent network can recognize trained objects from novel viewpoints.
  • The approach demonstrates potential for robust 3-D object recognition.

Conclusions:

  • The proposed method offers an effective solution for learning 3-D object representations from limited data.
  • This approach advances the field of computational vision by enabling viewpoint-invariant object recognition.
  • The technique holds promise for applications requiring robust visual object identification.