MegLoc: A Robust and Accurate Visual Localization Pipeline

TL;DR

MegLoc is a new visual localization pipeline that achieves high accuracy and robustness in diverse scenarios, including indoor, outdoor, seasonal, and long-term conditions, outperforming previous methods on multiple challenging datasets.

Contribution

The paper introduces MegLoc, a novel visual localization pipeline that significantly improves robustness and accuracy across various challenging environments and conditions.

Findings

Achieved state-of-the-art results on multiple challenging datasets.

Won the ICCV 2021 challenges for outdoor and indoor localization.

Demonstrated robustness across different seasons and years.

Abstract

In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years. MegLoc achieves state-of-the-art results on a range of challenging datasets, including winning the Outdoor and Indoor Visual Localization Challenge of ICCV 2021 Workshop on Long-term Visual Localization under Changing Conditions, as well as the Re-localization Challenge for Autonomous Driving of ICCV 2021 Workshop on Map-based Localization for Autonomous Driving.