OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive Uncertainty

TL;DR

This paper introduces OTPL-VIO, a robust stereo visual-inertial odometry system that uses optimal transport for line association and adaptive weighting to improve accuracy and stability in challenging environments.

Contribution

It proposes a novel deep descriptor for line segments and an entropy-regularized optimal transport method for consistent line matching in VIO.

Findings

Enhanced robustness in low-texture and illumination-challenging scenes.

Improved accuracy over baseline VIO systems.

Maintains real-time performance during deployment.

Abstract

Robust stereo visual-inertial odometry (VIO) remains challenging in low-texture scenes and under abrupt illumination changes, where point features become sparse and unstable, leading to ambiguous association and under-constrained estimation. Line structures offer complementary geometric cues, yet many efficient point-line systems still rely on point-guided line association, which can break down when point support is weak and may lead to biased constraints. We present a stereo point-line VIO system in which line segments are equipped with dedicated deep descriptors and matched using an entropy-regularized optimal transport formulation, enabling globally consistent correspondences under ambiguity, outliers, and partial observations. The proposed descriptor is training-free and is computed by sampling and pooling network feature maps. To improve estimation stability, we analyze the impact of line measurement noise and introduce reliability-adaptive weighting to regulate the influence of line constraints during optimization. Experiments on EuRoC and UMA-VI, together with real-world deployments in low-texture and illumination-challenging environments, demonstrate improved accuracy and robustness over representative baselines while maintaining real-time performance.