Learning to Estimate Scenes from Images

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. Advances in Neural Information Processing Systems, Vol. 11, M. S. Kearns, S. A. Solla and D. A. Cohn, eds., MIT Press, 1999 This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whol...

• Type: Conference
• Year: 1998
• Where: NIPS
• Authors: William T. Freeman, Egon C. Pasztor
• Keywords: Electric Research Laboratories, Mitsubishi Electric Research, NIPS 1998, NIPS 2007, Scene Interpretations