The purpose of this paper is to identify the similarities and differences between two image restoration approaches based on Markov field modeling. The first one is the well-known Bayesian approach which models the unknowns with a Markovian prior. In the second approach, as proposed by Pieczynski and Tebbache [1], the pair unknowns-observations as a whole is considered Markovian. The two approaches are compared based on their posterior distribution, synthetic results and real examples, when applied to the segmentation of degraded images.