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 generic viewpoint assumption and Bayesian inference.

M K Albert1

  • 1Vision Sciences Laboratory, Harvard University, Cambridge, MA 02138, USA. mka@soton.ac.uk

Perception
|September 19, 2000
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

Cue interactions, border ownership and illusory contours.

Vision research·2001
Same author

Surface formation and depth in monocular scene perception.

Perception·2001
Same author

The role of surface attraction in perceiving volumetric shape.

Perception·2000
Same author

The generic-viewpoint assumption and illusory contours.

Perception·2000
Same author

Assimilation of achromatic color cannot explain the brightness effects in the achromatic neon effect.

Perception·1999
Same author

Amodal completion in the absence of image tangent discontinuities.

Perception·1998
Same journal

Predictive models and parameter analysis for multiple tactile perceptions in skin-wet fabrics interface.

Perception·2026
Same journal

High-resolution kitsch by AI: Why society needs art, not more AI content.

Perception·2026
Same journal

Benchmarking spatial discrimination thresholds of two-frame motion defined forms compared to luminance and stereoscopic defined forms.

Perception·2026
Same journal

The effect of face masks on the perception of trustworthiness and competence in individuals with autistic traits.

Perception·2026
Same journal

The importance of external features for categorizing ethnicity: can Koreans identify Korean, Japanese, and Chinese faces?

Perception·2026
Same journal

Interoception, alexithymia, and motor congruency: Psychological drivers of body ownership in virtual reality.

Perception·2026
See all related articles

Human vision infers environmental information from retinal images. Reliability of visual inference, particularly the generic viewpoint assumption, depends on whether image coincidences involve features on the same object.

Area of Science:

  • Computational vision
  • Cognitive science
  • 3D scene reconstruction

Background:

  • Human vision infers environmental properties from retinal images, often requiring external knowledge.
  • The reliability of visual inference may depend on environmental regularities.
  • Previous work questioned the probabilistic validity of the generic viewpoint assumption under 'unbiased' priors.

Purpose of the Study:

  • To investigate the probabilistic validity of the generic viewpoint assumption in computer vision.
  • To explore the influence of feature co-occurrence on the reliability of visual inferences.
  • To differentiate between feature distributions in random 3D placements versus features on random 3D objects.

Main Methods:

  • Analysis of probability distributions for feature placement in 3D space.

Related Experiment Videos

  • Comparison of feature distributions on randomly placed features versus features on randomly shaped and posed objects.
  • Examination of the role of object identity in the interpretation of image coincidences.

    • Main Results:

    • The reliability of the generic viewpoint assumption is influenced by whether coincident image features belong to the same object.
    • Distinct probability distributions arise from random 3D feature placement versus features on random 3D objects.
    • Similar principles apply to inferring 3D motion from image motion.

    Conclusions:

    • The generic viewpoint assumption's validity is nuanced, depending on object-specific feature relationships.
    • Understanding feature distributions is crucial for reliable 3D inference from 2D images.
    • This research offers insights into the computational principles underlying human visual perception and 3D reconstruction.