Learning Low-Level Vision
|MERL Report: ||TR2000-05: William T. Freeman, Egon C. Pasztor, Owen T. Carmichael
International Journal of Computer 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, modelling 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 the 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 (simplified) problem domains. We learn to distinguish shading from reflectance variations in a single image. For the motion estimation problem, we show figure/ground discrimination, solution of the aperture problem, and filling-in arising from application of the same probabilistic machinery.