Learning low-level vision
Open Access
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1182-1189 vol.2
- https://doi.org/10.1109/iccv.1999.790414
Abstract
We show 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. We model that world with a Markov network, learning the network parameters from the examples. 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. 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.Keywords
This publication has 26 references indexed in Scilit:
- Turbo decoding as an instance of Pearl's "belief propagation" algorithmIEEE Journal on Selected Areas in Communications, 1998
- Iterative decoding of compound codes by probability propagation in graphical modelsIEEE Journal on Selected Areas in Communications, 1998
- Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature, 1996
- A Bayesian approach to image expansion for improved definitionIEEE Transactions on Image Processing, 1994
- Efficient multiscale regularization with applications to the computation of optical flowIEEE Transactions on Image Processing, 1994
- Parallel and deterministic algorithms from MRFs: surface reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Synthesizing a Color Algorithm from ExamplesScience, 1988
- Associative learning of scene parameters from imagesApplied Optics, 1987
- Relaxation labelling algorithms — a reviewImage and Vision Computing, 1985
- The Laplacian Pyramid as a Compact Image CodeIEEE Transactions on Communications, 1983