Discontinuous MRF prior and robust statistics: a comparative study

摘要

Discontinuity adaptive MRF priors have been used for modelling vision problems involving discontinuities,- and robust statistics models for solving regression problems involving outliers. This paper presents a comparative study of the two kinds of models. We analyse the mechanisms of adaptation (to discontinuities) and robustness (to outliers), and give a necessary condition for the adaptation and robustness. We then give a common definition of both models. The definition captures the essence of the adaptation ability, and in theory gives infinitely many choices of functions suitable for the adaptation in MRF and robust models. The likeness between the two models suggests that results in the two areas are interchangeable, to the benefit of each other.