Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)
Davi Geiger, Federico Girosi
Federico Girosi Artificial Intelligence Laboratory, MIT 545 Tech. Sq. # 788 Cambridge, MA 02139
In recent years many researchers have investigated the use of Markov Random Fields (MRFs) for computer vision. They can be applied for example to reconstruct surfaces from sparse and noisy depth data coming from the output of a visual process, or to integrate early vision processes to label physical discontinuities. In this pa(cid:173) per we show that by applying mean field theory to those MRFs models a class of neural networks is obtained. Those networks can speed up the solution for the MRFs models. The method is not restricted to computer vision.