ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting

TL;DR

ReefMapGS introduces a large-scale underwater reconstruction method that combines multimodal SLAM with Gaussian Splatting, enabling accurate scene modeling and vehicle localization without relying on traditional structure-from-motion.

Contribution

The paper presents ReefMapGS, a novel incremental reconstruction framework that integrates multimodal SLAM with Gaussian Splatting for efficient underwater scene mapping.

Findings

Reconstructed two complex underwater reef sites without COLMAP.

Achieved more accurate global pose estimation over 700 m trajectories.

Demonstrated effective scene expansion from high certainty regions.

Abstract

3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent on accurate camera poses typically obtained from computationally intensive processes like structure-from-motion that are unsuitable for field robot applications. However, in these domains, multimodal sensor data from acoustic, inertial, pressure, and visual sensors are available and suitable for pose-graph optimization-based SLAM methods that can estimate the vehicle's trajectory and thus our needed camera poses while providing uncertainty. We propose a 3DGS-based incremental reconstruction framework, ReefMapGS, that builds an initial model from a high certainty region and progressively expands to incorporate the whole scene. We reconstruct the scene incrementally by interleaving local tracking of new image observations with optimization of the underlying 3DGS scene. These refined poses are integrated back into the pose-graph to globally optimize the whole trajectory. We show COLMAP-free 3D reconstruction of two underwater reef sites with complex geometry as well as more accurate global pose estimation of our AUV over survey trajectories spanning up to 700 m.