Learning low-level vision

William T. Freeman, Egon C. Pasztor, Owen T. Carmichael

Research output: Contribution to journalArticlepeer-review

1219 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)25-47
Number of pages23
JournalInternational Journal of Computer Vision
Issue number1
StatePublished - Oct 2000
Externally publishedYes

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering


Dive into the research topics of 'Learning low-level vision'. Together they form a unique fingerprint.

Cite this