Can You Trust Your Pose? Confidence Estimation in Visual Localization
This addresses the critical need for trustworthy pose estimation in applications like autonomous navigation, though it is incremental as it builds on existing localization pipelines.
The paper tackles the problem of unreliable camera pose estimation in visual localization by introducing a novel confidence measure to quantify pose reliability, showing it can be applied flexibly across datasets and pipelines and improve accuracy with minimal computational overhead.
Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has focused on improving subcomponents of estimation pipelines, to achieve more accurate poses. However, there is no guarantee for the result to be correct, even though the correctness of pose estimation is critically important in several visual localization applications,such as in autonomous navigation. In this paper we bring to attention a novel research question, pose confidence estimation,where we aim at quantifying how reliable the visually estimated pose is. We develop a novel confidence measure to fulfil this task and show that it can be flexibly applied to different datasets,indoor or outdoor, and for various visual localization pipelines.We also show that the proposed techniques can be used to accomplish a secondary goal: improving the accuracy of existing pose estimation pipelines. Finally, the proposed approach is computationally light-weight and adds only a negligible increase to the computational effort of pose estimation.