Learning Object Representations from Lighting Variations

Abstract

Realistic representation of objects requires models which can synthesize the image of an object under all possible viewing conditions. We propose to learn these models from examples. Methods for learning surface geometry and albedo from one or more images under fixed posed and varying lighting conditions are described. Singular value decomposition (SVD) is used to determine shape, albedo, and lighting conditions up to an unknown 3x3 matrix, which is sufficient for recognition. The use of class-specific knowledge and the integrability constraint to determine this matrix is explored. We show that when the integrability constraint is applied to objects with varying albedo it leads to an ambiguity in depth estimation similar to the bas relief ambiguity. The integrability constraint, however, is useful for resolving ambiguities which arise in current photometric theories.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1996
Accession Number
AD1015521

Entities

People

  • A. L. Yuille
  • Peter N. Belhumeur
  • R. Epstein

Organizations

  • Harvard University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algebra
  • Algorithms
  • Applied Mathematics
  • Artificial Intelligence
  • Computer Science
  • Computer Vision
  • Eigenvalues
  • Electrical Engineering
  • Equations
  • Geometry
  • Light Sources
  • Linear Algebra
  • Mathematical Analysis
  • Object Recognition
  • Recognition
  • Surface Properties
  • Three Dimensional

Readers

  • Computer Vision.
  • Linear Algebra