Five-point Fundamental Matrix Estimation for Uncalibrated Cameras
This work addresses a specific bottleneck in computer vision for applications like urban scene analysis, though it is incremental in nature.
The paper tackles the problem of estimating the fundamental matrix from only five correspondences in uncalibrated cameras, achieving superior accuracy and efficiency compared to state-of-the-art methods, as validated on 561 real image pairs.
We aim at estimating the fundamental matrix in two views from five correspondences of rotation invariant features obtained by e.g.\ the SIFT detector. The proposed minimal solver first estimates a homography from three correspondences assuming that they are co-planar and exploiting their rotational components. Then the fundamental matrix is obtained from the homography and two additional point pairs in general position. The proposed approach, combined with robust estimators like Graph-Cut RANSAC, is superior to other state-of-the-art algorithms both in terms of accuracy and number of iterations required. This is validated on synthesized data and $561$ real image pairs. Moreover, the tests show that requiring three points on a plane is not too restrictive in urban environment and locally optimized robust estimators lead to accurate estimates even if the points are not entirely co-planar. As a potential application, we show that using the proposed method makes two-view multi-motion estimation more accurate.