Learning Low-Level Vision


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.

DOI: 10.1023/A:1026501619075
View Slides

Extracted Key Phrases

29 Figures and Tables

Citations per Year

1,294 Citations

Semantic Scholar estimates that this publication has 1,294 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Freeman1999LearningLV, title={Learning Low-Level Vision}, author={William T. Freeman and Egon C. Pasztor and Owen T. Carmichael}, journal={International Journal of Computer Vision}, year={1999}, volume={40}, pages={25-47} }