SURGE: Sonar-fUsed Reconstruction and localization via image-gated Graph Estimation

2026-10-05

AI Summary

This study addresses the challenges of visual scale ambiguity, trajectory drift, and sonar geometric incompleteness in underwater robots caused by the absence of external localization. To overcome these limitations, we propose SURGE, a framework that for the first time deeply fuses visual and acoustic observations within a factor graph to jointly estimate ROV trajectories and target positions. The recovered metric poses are then leveraged to drive Sonar Gaussian Splatting for three-dimensional reconstruction, breaking through the constraints of conventional decoupled processing pipelines. Experimental results demonstrate that the proposed framework significantly improves localization consistency and generates high-quality 3D reconstructions that are more compact and possess native metric scale compared to purely RGB-based baselines.

Abstract

Remotely operated vehicles (ROVs) are widely used to explore and inspect underwater environments such as caves, shipwrecks, and submerged infrastructure. These missions require accurate 3D understanding of the surrounding environment, which depends on both reliable vehicle localization and metric scene reconstruction. However, external positioning is often unavailable underwater, requiring small ROVs to rely primarily on onboard perception. Optic vision provides rich visual and geometric information but suffers from scale ambi- guity and trajectory drift, whereas 2D imaging sonar provides metric range but incomplete 3D geometry. Existing underwater reconstruction approaches typically address these limitations separately or assume known sensor poses, leaving localization and reconstruction disconnected. We present SURGE, a camera sonar framework that jointly estimates the ROV trajectory and target location by integrating visual and acoustic observations within a factor graph, then uses the recovered metric poses for sonar Gaussian splatting. Experiments on real underwater RGB sonar observations show that SURGE substantially improves localization consistency over conventional vision based pose estimation and produces a more compact, natively metric reconstruction than RGB Gaussian splatting baselines.

Problem

• underwater localization
• 3D scene reconstruction
• camera-sonar fusion
• remotely operated vehicles

Innovation

• Factor Graph
• Camera-Sonar Fusion
• Gaussian Splatting
• Underwater Localization
• 3D Reconstruction