OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications

TL;DR

OV$^{2}$SLAM is a versatile, fully online visual SLAM system capable of real-time operation across various camera setups, scales, and frame-rates, demonstrating state-of-the-art accuracy and robustness.

Contribution

It introduces a fully online, multi-threaded visual SLAM algorithm that handles monocular and stereo cameras with diverse operational parameters, advancing real-time SLAM capabilities.

Findings

Achieves state-of-the-art accuracy in visual SLAM tasks.

Operates in real-time across different camera configurations and frame-rates.

Provides open-source implementation for community use.

Abstract

Many applications of Visual SLAM, such as augmented reality, virtual reality, robotics or autonomous driving, require versatile, robust and precise solutions, most often with real-time capability. In this work, we describe OV$^{2}$SLAM, a fully online algorithm, handling both monocular and stereo camera setups, various map scales and frame-rates ranging from a few Hertz up to several hundreds. It combines numerous recent contributions in visual localization within an efficient multi-threaded architecture. Extensive comparisons with competing algorithms shows the state-of-the-art accuracy and real-time performance of the resulting algorithm. For the benefit of the community, we release the source code: \url{https://github.com/ov2slam/ov2slam}.