Efficient and Scalable 4th-Order Match Propagation

Abstract

Abstract. We propose a robust method to match image feature points taking into account geometric consistency. It is a careful adaptation of the match propagation principle to 4th-order geometric constraints (match quadruple consistency). With our method, a set of matches is explained by a network of locally-similar affinities. This approach is useful when simple descriptor-based matching strategies fail, in particular for highly ambiguous data, e.g., with repetitive patterns or where texture is lacking. As it scales easily to hundreds of thousands of matches, it is also useful when denser point distributions are sought, e.g., for high-precision rigid model estimation. Experiments show that our method is competitive (efficient, scalable, accurate, robust) against state-of-the-art methods in deformable object matching, camera calibration and pattern detection.

Multiple Non-rigid Surface Detection and Registration

“…However, it heavily depends on the affine-covariant feature detectors and thus not applicable to other features. As shown in [22], affine shape determination is not accurate and thus shape adaptation can be noisy. Our method for correspondence clustering aims to overcome the above drawbacks.…”