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 intothe computer vision field about two decades ago, while they started to become a ubiquitous tool forsolving visual perception problems at the turn of the millennium following the emergence of efficientinference methods. During the past decade, different MRF models as well as inference methods - in particular those based on discrete optimization - have been developed towards addressing numerous vision problems of low, mid and high level. While most of the literature concerns pairwise MRFs, during recent years, we have also witnessed significant progress on higher-order MRFs, which substantially enhances the expressiveness of graph-based models and enlarges the extent of solvable problems. We hope that this survey will provide a compact and informative summary of the main literature in this research topic.