Example Based Image Analysis and Synthesis

Abstract

Image analysis and graphics synthesis can be achieved with learning techniques using directly image examples without physically-based, 3D models. In our technique: -- the mapping from novel images to a vector of 'pose' and 'expression' parameters can be learned from a small set of example images using a function approximation technique that we call an analysis network; -- the inverse mapping from input 'pose' and 'expression' parameters to output images can be synthesized from a smallset of example images and used to produce new images using a similar synthesis network. The techniques described here have several applications in computer graphics, special effects, interactive multimedia and very low bandwidth teleconferencing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1993
Accession Number
ADA282285

Entities

People

  • Amnon Shashua
  • David Beymer
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Cognitive Science
  • Computational Science
  • Computer Graphics
  • Computer Vision
  • Computers
  • Eigenvectors
  • Equations
  • Geometry
  • Graphics
  • Image Compression
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Teleconferencing
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Vision.