Benchmarking Visual Feature Representations for LiDAR-Inertial-Visual Odometry Under Challenging Conditions

TL;DR

This paper introduces a hybrid visual odometry framework combining direct and descriptor-based methods, improving robustness and accuracy in challenging environments for autonomous vehicle localization.

Contribution

It extends the FAST-LIVO2 framework by integrating various visual descriptors with direct methods and benchmarks their performance under difficult conditions.

Findings

Hybrid approach outperforms sparse-direct methods in accuracy and robustness.

Learning-based descriptors maintain performance under illumination changes.

Hybrid method shows improved feature tracking stability.

Abstract

Accurate localization in autonomous driving is critical for successful missions including environmental mapping and survivor searches. In visually challenging environments, including low-light conditions, overexposure, illumination changes, and high parallax, the performance of conventional visual odometry methods significantly degrade undermining robust robotic navigation. Researchers have recently proposed LiDAR-inertial-visual odometry (LIVO) frameworks, that integrate LiDAR, IMU, and camera sensors, to address these challenges. This paper extends the FAST-LIVO2-based framework by introducing a hybrid approach that integrates direct photometric methods with descriptor-based feature matching. For the descriptor-based feature matching, this work proposes pairs of ORB with the Hamming distance, SuperPoint with SuperGlue, SuperPoint with LightGlue, and XFeat with the mutual nearest neighbor. The proposed configurations are benchmarked by accuracy, computational cost, and feature tracking stability, enabling a quantitative comparison of the adaptability and applicability of visual descriptors. The experimental results reveal that the proposed hybrid approach outperforms the conventional sparse-direct method. Although the sparse-direct method often fails to converge in regions where photometric inconsistency arises due to illumination changes, the proposed approach still maintains robust performance under the same conditions. Furthermore, the hybrid approach with learning-based descriptors enables robust and reliable visual state estimation across challenging environments.