Feature matching using quasi-conformal maps

Chunxue Wang, Ligang Liu

Abstract: We present a fully automatic method for finding geometrically consistent correspondences while discarding outliers from the candidate point matches in two images. Given a set of candidate matches provided by scale-invariant feature transform (SIFT) descriptors, which may contain many outliers, our goal is to select a subset of these matches retaining much more geometric information constructed by a mapping searched in the space of all diffeomorphisms. This problem can be formulated as a constrained optimization involving both the Beltrami coefficient (BC) term and quasi-conformal map, and solved by an efficient iterative algorithm based on the variable splitting method. In each iteration, we solve two subproblems, namely a linear system and linearly constrained convex quadratic programming. Our algorithm is simple and robust to outliers. We show that our algorithm enables producing more correct correspondences experimentally compared with state-of-the-art approaches.