TY - GEN
T1 - Minimal Solutions for Relative Pose with a Single Affine Correspondence
AU - Guan, Banglei
AU - Zhao, Ji
AU - Li, Zhang
AU - Sun, Fang
AU - Fraundorfer, Friedrich
N1 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
PY - 2020/6/15
Y1 - 2020/6/15
N2 - In this paper we present four cases of minimal solutions for two-view relative pose estimation by exploiting the affine transformation between feature points and we demonstrate efficient solvers for these cases. It is shown, that under the planar motion assumption or with knowledge of a vertical direction, a single affine correspondence is sufficient to recover the relative camera pose. The four cases considered are two-view planar relative motion for calibrated cameras as a closed-form and a least-squares solution, a closed-form solution for unknown focal length and the case of a known vertical direction. These algorithms can be used efficiently for outlier detection within a RANSAC loop and for initial motion estimation. All the methods are evaluated on both synthetic data and real-world datasets from the KITTI benchmark. The experimental results demonstrate that our methods outperform comparable state-of-the-art methods in accuracy with the benefit of a reduced number of needed RANSAC iterations
AB - In this paper we present four cases of minimal solutions for two-view relative pose estimation by exploiting the affine transformation between feature points and we demonstrate efficient solvers for these cases. It is shown, that under the planar motion assumption or with knowledge of a vertical direction, a single affine correspondence is sufficient to recover the relative camera pose. The four cases considered are two-view planar relative motion for calibrated cameras as a closed-form and a least-squares solution, a closed-form solution for unknown focal length and the case of a known vertical direction. These algorithms can be used efficiently for outlier detection within a RANSAC loop and for initial motion estimation. All the methods are evaluated on both synthetic data and real-world datasets from the KITTI benchmark. The experimental results demonstrate that our methods outperform comparable state-of-the-art methods in accuracy with the benefit of a reduced number of needed RANSAC iterations
KW - cs.CV
UR - http://www.scopus.com/inward/record.url?scp=85093082272&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.00200
DO - 10.1109/CVPR42600.2020.00200
M3 - Conference paper
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1926
EP - 1935
BT - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE Publications
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Y2 - 14 June 2020 through 19 June 2020
ER -