MARVO: Marine-Adaptive Radiance-aware Visual Odometry

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sundar, Sacchin, Kikani, Atman, Alam, Aaliya, Shrote, Sumukh, Khan, A. Nayeemulla, Shahina, A.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912735072092160
author Sundar, Sacchin
Kikani, Atman
Alam, Aaliya
Shrote, Sumukh
Khan, A. Nayeemulla
Shahina, A.
author_facet Sundar, Sacchin
Kikani, Atman
Alam, Aaliya
Shrote, Sumukh
Khan, A. Nayeemulla
Shahina, A.
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2511_22860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MARVO: Marine-Adaptive Radiance-aware Visual Odometry
Sundar, Sacchin
Kikani, Atman
Alam, Aaliya
Shrote, Sumukh
Khan, A. Nayeemulla
Shahina, A.
Robotics
Computer Vision and Pattern Recognition
I.4.7
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).
title MARVO: Marine-Adaptive Radiance-aware Visual Odometry
topic Robotics
Computer Vision and Pattern Recognition
I.4.7
url https://arxiv.org/abs/2511.22860