Metric Monocular Localization Using Signed Distance Fields
This addresses metric localization for vision-based navigation systems, particularly in environments with appearance changes, though it appears incremental as it builds on prior geometry-based methods.
The paper tackles metric localization for monocular cameras by using Signed Distance Fields (SDFs) as a global map representation to relax the need for accurate structure from local Bundle Adjustment, achieving comparable performance to state-of-the-art methods with minimal sensor configuration on indoor and outdoor datasets.
Metric localization plays a critical role in vision-based navigation. For overcoming the degradation of matching photometry under appearance changes, recent research resorted to introducing geometry constraints of the prior scene structure. In this paper, we present a metric localization method for the monocular camera, using the Signed Distance Field (SDF) as a global map representation. Leveraging the volumetric distance information from SDFs, we aim to relax the assumption of an accurate structure from the local Bundle Adjustment (BA) in previous methods. By tightly coupling the distance factor with temporal visual constraints, our system corrects the odometry drift and jointly optimizes global camera poses with the local structure. We validate the proposed approach on both indoor and outdoor public datasets. Compared to the state-of-the-art methods, it achieves a comparable performance with a minimal sensor configuration.