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 computational model for shape from texture

J Malik1, R Rosenholtz

  • 1Department of Electrical Engineering and Computer Science, University of California at Berkeley 94720.

Ciba Foundation Symposium
|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

Real-world patterns of treatment and response in metastatic renal cell carcinoma: a multicentre UK-wide review with UK Renal Oncology Collaborative (UK ROC).

ESMO real world data and digital oncology·2026
Same author

Three versus six cycles of platinum-based chemotherapy followed by avelumab maintenance as first-line treatment for advanced urothelial cancer: the phase II DISCUS trial.

Annals of oncology : official journal of the European Society for Medical Oncology·2025
Same author

First Real-Time Imaging of Acute Effects of Arteriovenous Fistula on Regional Distribution of Pulmonary Perfusion in a Novel Porcine Model.

Physiological research·2025
Same author

Cardiorenal Syndromes and Their Role in Water and Sodium Homeostasis.

Physiological research·2024
Same author

Bosworth ankle dislocation fracture - current concept review.

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2024
Same author

Clinical and radiological results of TLIF surgery with titanium-coated PEEK or uncoated PEEK cages: a prospective single-centre randomised study.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2023
Same journal

Precision agriculture: spatial and temporal variability of environmental quality. General reflections.

Ciba Foundation symposium·1997
Same journal

Uncertainty in hydrogeological modelling.

Ciba Foundation symposium·1997
Same journal

Optimal mapping of site-specific multivariate soil properties.

Ciba Foundation symposium·1997
Same journal

Modelling for precision weed management.

Ciba Foundation symposium·1997
Same journal

GIS support for precision agriculture: problems and possibilities.

Ciba Foundation symposium·1997
Same journal

Spatial sampling.

Ciba Foundation symposium·1997
See all related articles

This study presents a novel two-stage framework for shape from texture analysis. It models texture distortion using affine transformations to infer 3D surface shape and orientation from images.

Area of Science:

  • Computer Vision
  • Computational Geometry
  • Image Analysis

Background:

  • Shape from texture is a crucial area in computer vision for inferring 3D surface properties from 2D images.
  • Existing methods often require explicit texel identification or restrictive assumptions about texture properties.

Purpose of the Study:

  • To develop a robust framework for shape from texture analysis.
  • To model texture distortion as an affine transformation for inferring surface shape and orientation.

Main Methods:

  • A two-stage framework analogous to stereopsis and structure from motion.
  • Modeling texture distortion using affine transformations derived from differential analysis of image patches.
  • Developing two models for recovering surface orientation (slant, tilt) and shape (principal curvatures, directions).

Related Experiment Videos

Main Results:

  • A technique for estimating affine transforms between image patches without explicit texel identification.
  • Successful recovery of surface orientation and shape from planar and curved surfaces.
  • Demonstrated robustness without restrictive assumptions on image texture isotropy.

Conclusions:

  • The proposed affine transformation-based approach provides an effective method for shape from texture analysis.
  • The framework accurately infers 3D surface properties from image texture distortions.
  • Experimental results validate the technique on various surface types under perspective projection.