The paper revisits the problem of local optimization for RANSAC. Improvements of the LO-
RANSAC procedure are proposed: a use of truncated quadratic cost function, an …

This paper proposes a geometric interpretation of the angles and scales which the
orientation-and scale-covariant feature detectors, eg SIFT, provide. Two new general …

Local features eg. SIFT and its affine and learned variants provide region-to-region rather
than point-to-point correspondences. This has recently been exploited to create new …

Abstract Affine Correspondences (ACs) are more informative than Point Correspondences
(PCs) that are used as input in mainstream algorithms for Structure-from-Motion (SfM). Since …

We propose a method to estimate the essential matrix using two affine correspondences for
a pair of calibrated perspective cameras. Two novel, linear constraints are derived between …

We aim at estimating the fundamental matrix in two views from five correspondences of
rotation invariant features obtained by eg the SIFT detector. The proposed minimal solver …

An approach is proposed for recovering affine correspondences (ACs) from orientation-and
scale-covariant, eg, SIFT, features exploiting pre-estimated epipolar geometry. The method …

We derive an explicit relation between local affine approximations resulting from matching of
affine invariant regions and the epipolar geometry in the case of a two view geometry. Most …

A minimal solution using two affine correspondences is presented to estimate the common
focal length and the fundamental matrix between two semi-calibrated cameras-known …

This paper derives the geometric relationship of epipolar geometry and orientation-and
scale-covariant, eg, SIFT, features. We derive a new linear constraint relating the unknown …