In this paper, we present a comprehensive survey of Markov Random Fields (MRFs) in computer vision, with respect to both the modeling and the inference. MRFs were introduced into the computer vision field about two decades ago, while they started to become a ubiquitous tool for solving visual perception problems at the turn of the millennium following the emergence of efficient inference method...

Born 1963; diploma in architecture and in civil engineering; Ph.D. in structural engineering RWTH Aachen; founder of Bureau d’études Weinand, Liège; professor at EPFL and director of the IBOIS/EPFL Lausanne; co-founder of SHEL Architecture Engineering and Production Design, Geneva. Olivier BAVEREL Associate Prof. Dr. Navier Research center, ENPC, Champs-sur-Marne ENSAG, France [email protected]