Towards Revisiting Visual Place Recognition for Joining Submaps in Multimap SLAM

TL;DR

This paper explores how modern visual place recognition (VPR) methods can improve submap merging in multimap SLAM systems, proposing a new evaluation pipeline and demonstrating enhanced performance on benchmark datasets.

Contribution

It introduces a post-processing pipeline and metrics for assessing modern VPR components' impact on SLAM, and proposes a simple method combining VPR with temporal consistency for better map merging.

Findings

Modern VPR approaches can enhance submap merging in SLAM.

The proposed metrics effectively estimate VPR impact on SLAM performance.

Combining VPR with temporal consistency improves map merging results.

Abstract

Visual SLAM is a key technology for many autonomous systems. However, tracking loss can lead to the creation of disjoint submaps in multimap SLAM systems like ORB-SLAM3. Because of that, these systems employ submap merging strategies. As we show, these strategies are not always successful. In this paper, we investigate the impact of using modern VPR approaches for submap merging in visual SLAM. We argue that classical evaluation metrics are not sufficient to estimate the impact of a modern VPR component on the overall system. We show that naively replacing the VPR component does not leverage its full potential without requiring substantial interference in the original system. Because of that, we present a post-processing pipeline along with a set of metrics that allow us to estimate the impact of modern VPR components. We evaluate our approach on the NCLT and Newer College datasets using ORB-SLAM3 with NetVLAD and HDC-DELF as VPR components. Additionally, we present a simple approach for combining VPR with temporal consistency for map merging. We show that the map merging performance of ORB-SLAM3 can be improved. Building on these results, researchers in VPR can assess the potential of their approaches for SLAM systems.