Structureless VIO

TL;DR

This paper introduces a novel structureless visual-inertial odometry method that removes the need for a visual map, leading to improved computational efficiency and accuracy over traditional structure-based approaches.

Contribution

The paper proposes a new structureless VIO framework that eliminates the visual map, enhancing efficiency and accuracy compared to existing methods.

Findings

Significantly improves computational efficiency.

Achieves better accuracy than structure-based VIO.

Demonstrates effectiveness through experimental results.

Abstract

Visual odometry (VO) is typically considered as a chicken-and-egg problem, as the localization and mapping modules are tightly-coupled. The estimation of a visual map relies on accurate localization information. Meanwhile, localization requires precise map points to provide motion constraints. This classical design principle is naturally inherited by visual-inertial odometry (VIO). Efficient localization solutions that do not require a map have not been fully investigated. To this end, we propose a novel structureless VIO, where the visual map is removed from the odometry framework. Experimental results demonstrated that, compared to the structure-based VIO baseline, our structureless VIO not only substantially improves computational efficiency but also has advantages in accuracy.