MARVO: Marine-Adaptive Radiance-aware Visual Odometry

TL;DR

MARVO is an underwater visual odometry system that combines physics-based modeling, deep learning, and reinforcement learning to improve localization accuracy in challenging underwater environments.

Contribution

It introduces a physics-aware radiance adapter, a semi-dense feature matching method, and a reinforcement learning-based pose graph optimizer for underwater localization.

Findings

Achieves robust feature matching under turbidity and color attenuation.

Provides real-time full-state pose estimation combining visual, inertial, and barometric data.

Refines global trajectories beyond classical optimization methods.

Abstract

Underwater visual localization remains challenging due to wavelength-dependent attenuation, poor texture, and non-Gaussian sensor noise. We introduce MARVO, a physics-aware, learning-integrated odometry framework that fuses underwater image formation modeling, differentiable matching, and reinforcement-learning optimization. At the front-end, we extend transformer-based feature matcher with a Physics Aware Radiance Adapter that compensates for color channel attenuation and contrast loss, yielding geometrically consistent feature correspondences under turbidity. These semi dense matches are combined with inertial and pressure measurements inside a factor-graph backend, where we formulate a keyframe-based visual-inertial-barometric estimator using GTSAM library. Each keyframe introduces (i) Pre-integrated IMU motion factors, (ii) MARVO-derived visual pose factors, and (iii) barometric depth priors, giving a full-state MAP estimate in real time. Lastly, we introduce a Reinforcement-Learningbased Pose-Graph Optimizer that refines global trajectories beyond local minima of classical least-squares solvers by learning optimal retraction actions on SE(2).