Learning to Estimate Scenes from Images
Abstract
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames (image). From synthetic data , we model the relationship between image and scene patches, and between a scene patch and neighboring scene patches. Given' a new image, we propagate likelihoods in a Markov network (ignoring the effect of loops) to infer the underlying scene. This yields an efficient method to form low-level scene interpretations. We demonstrate the technique for motion analysis and estimating high resolution images from low-resolution ones.
Cite
Text
Freeman and Pasztor. "Learning to Estimate Scenes from Images." Neural Information Processing Systems, 1998.Markdown
[Freeman and Pasztor. "Learning to Estimate Scenes from Images." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/freeman1998neurips-learning/)BibTeX
@inproceedings{freeman1998neurips-learning,
title = {{Learning to Estimate Scenes from Images}},
author = {Freeman, William T. and Pasztor, Egon C.},
booktitle = {Neural Information Processing Systems},
year = {1998},
pages = {775-781},
url = {https://mlanthology.org/neurips/1998/freeman1998neurips-learning/}
}