Computational visual perception seeks to reproduce human vision through the combination of visual sensors, artificial intelligence andcomputing. To this end, computer vision tasks are often reformulated as mathematical inference problems where the objective is to determine the set of parameters corresponding to the lowest potential of a task-specific objective function. Graphical models have been the mostpopular formulation in the field over the past two decades where the problem is viewed as an discrete assignment labeling one. Modularity, scalability and portability are the main strength of these methods which once combined with efficient inference algorithms they could leadto state of the art results. In this tutorial we focus on t...