Global Motion Estimation from Point Matches

215 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Geometric Deep Learning: Going beyond Euclidean data (2016, background): “perators, e.g., functional correspondences [3] or difference operators [4] in a collection of 3D shapes, or orientations of overlapping cameras in multi-view vision (“structure from motion”) problems [5]. The complexity of geometric data and the availability of very large datasets (in the case of so”
A Survey on Structure from Motion (2017, methodology): “However, the problem (21) (and its variations using robust cost functions instead of the sum of squared deviations in (21)) was shown in the literature to admit high quality approximations via convex relaxations and spectral methods (cf., e.g., [4, 54, 12, 81, 16]).”
Robust Global Translations with 1DSfM (2014, methodology): “objective function that depends only on comparing measurement directions to model directions, as opposed to other methods [11,3] where the objective function is also a function of the distance between images.”