Skip to Main Content
When image primitives cannot be robustly extracted, the estimation of a perspective transformation between overlapping images can be formulated as a markov random field (MRF) and minimized efficiently using graph cuts. For well contrasted images with low noise level, a first order MRF leads to an accurate and robust registration. With increasing noise however, the registration quality decreases rapidly. This contribution presents a novel algorithm that enforces planarity (as required for perspective transformations) as a soft constraint by adding higher-order cliques to the energy formulation. Results show that for low levels of Gaussian noise (standard deviation σn ϵ [0,4]), the algorithm performs comparably to the standard first order formulation. For increasing levels of noise (σn ϵ [5,12]), the found solution is roughly twice as accurate (deviation of ≈2 pixels on average compared to ≈4 pixels for σn = 10).