Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation

Robust cost optimization is the task of fitting parameters to data points containing outliers. In particular, we focus on large-scale computer vision problems, such as bundle adjustment, where Non-Linear Least Square (NLLS) solvers are the current workhorse. In this context, NLLS-based state of the...

Full description

Saved in:
Bibliographic Details
Published in17th IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, South Korea Vol. 2019-October; pp. 10242 - 10250
Main Authors Zach, Christopher, Bourmaud, Guillaume
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2019
Subjects
3D reconstruction
Computer vision
Computer vision problems
Cost function
epipolar geometry
Estimation
Kernel
Minimization
Multiobjective optimization
Robustness
structure from motion
Online AccessGet full text

Cover

More Information
Summary:Robust cost optimization is the task of fitting parameters to data points containing outliers. In particular, we focus on large-scale computer vision problems, such as bundle adjustment, where Non-Linear Least Square (NLLS) solvers are the current workhorse. In this context, NLLS-based state of the art algorithms have been designed either to quickly improve the target objective and find a local minimum close to the initial value of the parameters, or to have a strong ability to escape poor local minima. In this paper, we propose a novel algorithm relying on multi-objective optimization which allows to match those two properties. We experimentally demonstrate that our algorithm has an ability to escape poor local minima that is on par with the best performing algorithms with a faster decrease of the target objective.
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2019.01034