Abstract

Affine Correspondences (ACs) are more informative thanPoint Correspondences (PCs) that are used as input inmainstream algorithms for Structure-from-Motion (SfM).Since ACs enable to estimate models from fewer correspon-dences, its use can dramatically reduce the number of com-binations during the iterative step of sample-and-test that exists in most SfM pipelines. However, using ACs instead of PCs as input for SfM passes by fully understanding the relations between ACs and multi-view geometry, as well as by establishing practical, effective AC-based algorithms. This article is a step forward into this direction, by providing a clear account about how ACs constrain the two-view geom-etry, and by proposing new algorithms for plane segmen-tation and visual odometry that compare favourably with respect to methods relying in PCs.