Efficient energy-based topological outlier rejection

Abstract

An approach is proposed for outlier rejection from a set of 2D point correspondences which does not require any underlying models, e.g. fundamental matrix. The solution is obtained by minimizing an energy originated from the neighborhood-graphs in both images using a grab-cut-like algorithm: iterated graph-cut and re-fitting. The method is validated on publicly available datasets, it is real time for most of the problems and achieves more accurate results than RANSAC and its state-of-the-art variants in terms of outlier rejection ratio. It is applicable to scenes where a single fundamental matrix is not estimable, e.g. non-rigid or degenerate ones.