Lidé
MSc. Charalampos Tzamos
Všechny publikace
Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?
- Autoři: MSc. Charalampos Tzamos, Kocur, V., Yaqing Ding, Ph.D., Sattler, T., RNDr. Zuzana Kúkelová, Ph.D.,
- Publikace: ECCV 2024 Workshops - Half-Century of Structure-from-Motion. Cham: Springer Nature Switzerland AG, 2025. p. 91-107. vol. 15623. ISSN 0302-9743. ISBN 978-3-031-91568-0.
- Rok: 2025
- DOI: 10.1007/978-3-031-91569-7_7
- Odkaz: https://doi.org/10.1007/978-3-031-91569-7_7
- Pracoviště: Skupina vizuálního rozpoznávání
-
Anotace:
Estimating the relative pose between two cameras is a fundamental step in many applications such as Structure-from-Motion. The common approach to relative pose estimation is to apply a minimal solver inside a RANSAC loop. Highly efficient solvers exist for pinhole cameras. Yet, (nearly) all cameras exhibit radial distortion. Not modeling radial distortion leads to (significantly) worse results. However, minimal radial distortion solvers are significantly more complex than pinhole solvers, both in terms of run-time and implementation efforts. This paper compares radial distortion solvers with a simple-to-implement baseline that combines an efficient pinhole solver with sampled radial distortion parameters. Extensive experiments on multiple datasets and RANSAC variants show that this simple baseline performs similarly or better than the most accurate minimal distortion solvers at faster run-times while being significantly more accurate than faster non-minimal solvers. Our results clearly show that complex radial distortion solvers are not necessary in practice. We will make the code and a new benchmark available.