3D Surfel Map-Aided Visual Relocalization with Learned Descriptors

TL;DR

This paper presents a novel visual relocalization method that leverages 3D surfel maps and learned descriptors to accurately estimate camera poses in complex environments, demonstrating improved robustness and efficiency.

Contribution

The method integrates 3D surfel map geometry with learned descriptors for enhanced visual relocalization accuracy and robustness in challenging scenarios.

Findings

Effective in real-world and simulated environments

Provides consistent alignment with 3D environment

Improves performance in challenging cases

Abstract

In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map. A visual database is first built by global indices from the 3D surfel map rendering, which provides associations between image points and 3D surfels. Surfel reprojection constraints are utilized to optimize the keyframe poses and map points in the visual database. A hierarchical camera relocalization algorithm then utilizes the visual database to estimate 6-DoF camera poses. Learned descriptors are further used to improve the performance in challenging cases. We present evaluation under real-world conditions and simulation to show the effectiveness and efficiency of our method, and make the final camera poses consistently well aligned with the 3D environment.