Linear Relative Pose Estimation Founded on Pose-only Imaging Geometry
This work addresses a critical issue in computer vision for applications like 3D reconstruction and robotics, offering a robust solution for outlier removal in relative pose estimation, though it is incremental as it builds on existing methods like IRLS and RANSAC.
The paper tackles the problem of efficiently and accurately handling image matching outliers in two-view relative pose estimation by introducing a linear algorithm that filters outliers using pose-only imaging geometry and reweighting. It achieves a relative rotation accuracy improvement of 2 to 10 times when facing up to 80% outliers, as shown in simulations and tests on the Strecha dataset.
How to efficiently and accurately handle image matching outliers is a critical issue in two-view relative estimation. The prevailing RANSAC method necessitates that the minimal point pairs be inliers. This paper introduces a linear relative pose estimation algorithm for n $( n \geq 6$) point pairs, which is founded on the recent pose-only imaging geometry to filter out outliers by proper reweighting. The proposed algorithm is able to handle planar degenerate scenes, and enhance robustness and accuracy in the presence of a substantial ratio of outliers. Specifically, we embed the linear global translation (LiGT) constraint into the strategies of iteratively reweighted least-squares (IRLS) and RANSAC so as to realize robust outlier removal. Simulations and real tests of the Strecha dataset show that the proposed algorithm achieves relative rotation accuracy improvement of 2 $\sim$ 10 times in face of as large as 80% outliers.