Internation Journal of Computer Vision manuscript No. (will be inserted by the editor) Imposing Semi-local Geometric Constraints for Accurate Correspondences Selection in Structure from Motion: a Game-Theoretic Perspective

based on the iterative refinement of an initial batch of feature correspondences. Typically this is performed by selecting a set of match candidates based on their pho-tometric similarity; an initial estimate of camera intrin-sic and extrinsic parameters is then computed by min-imizing the reprojection error. Finally, outliers in the initial correspondences are filtered by enforcing some global geometric property such as the epipolar con-straint. In the literature many different approaches have been proposed to deal with each of these three steps, but almost invariably they separate the first inlier se-lection step, which is based only on local image prop-erties, from the enforcement of global geometric con-sistency. Unfortunately, these two steps are not inde-pendent since outliers can lead to inaccurate parame-ter estimation or even prevent convergence, leading to the well known sensitivity of all filtering approaches to the number of outliers, especially in the presence of structured noise, which can arise, for example, when the images present several repeated patterns. In this paper we introduce a novel stereo correspondence selection scheme that casts the problem into a Game-Theoretic framework in order to guide the inlier selection toward