Learning Low-Level Vision

  • Authors:

  • William T. Freeman;Egon C. Pasztor;Owen T. Carmichael

  • Affiliations:

  • Mitsubishi Electric Research Labs., 201 Broadway, Cambridge, MA 02139. Freeman@merl.com;MIT Media Laboratory, E15-385, 20 Ames st. Cambridge, MA, 02139. egon@media.mit.edu;209 Smith Hall, Carnegie-Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213. otc@andrew.cmu.edu

  • Venue:
  • International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
  • Year:
  • 2000

Quantified Score

Hi-index 0.14

Visualization

Abstract

We describe a learning-based method for low-level vision problems—estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, modeling their relationships with a Markov network. Bayesian belief propagation allows us to efficiently find a local maximum of the posterior probability for the scene, given an image. We call this approach VISTA—Vision by Image/Scene TrAining.We apply VISTA to the “super-resolution” problem (estimating high frequency details from a low-resolution image), showing good results. To illustrate the potential breadth of the technique, we also apply it in two other problem domains, both simplified. We learn to distinguish shading from reflectance variations in a single image under particular lighting conditions. For the motion estimation problem in a “blobs world”, we show figure/ground discrimination, solution of the aperture problem, and filling-in arising from application of the same probabilistic machinery.