APVI-SLAM: Real-Time Acoustic-Pressure-Visual-Inertial Localization and Photorealistic Mapping System in Complex Underwater Environment

2026-07-07

AI Summary

This work addresses localization drift and mapping distortion in complex underwater environments caused by visual degradation by proposing a multimodal tightly coupled SLAM system that fuses acoustic, pressure, visual, and inertial measurements. Robustness is enhanced through reliability-aware dynamic sensor weighting and a sliding-window freezing-and-recovery mechanism. The study introduces a novel quadtree-guided underwater light propagation model and a 3D Gaussian splatting optimization method to achieve high-fidelity photorealistic reconstruction. Key contributions include a new multisensor fusion framework, the release of the first underwater coral reef dataset featuring synchronized multimodal data, and state-of-the-art performance in real-time, high-precision localization and photorealistic 3D reconstruction on both public and self-collected datasets.

Abstract

Extreme subsea environments often cause severe feature de-gradation and estimator divergence in underwater visual-inertial SLAM. Although sensors like Doppler Velocity Logs (DVL) and pressure gauges provide auxiliary constraints, robust multi-sensor fusion during intermittent visual failure remains challenging. To address this, we present APVI-SLAM, a real-time multi-sensor fusion SLAM system that achieves both accurate underwater localization and photorealistic mapping. Our approach introduces a reliability-aware localization framework that dynamically reweights sensor estimators and employs a sliding-window freezing strategy to recover from tracking failures, substantially enhancing system robustness. Furthermore, for high-fidelity scenes reconstruction, we propose an efficient quadtree-guided mapping module that facilitates incremental water-medium modeling and 3D Gaussian optimization. Recognizing the lack of benchmark for underwater mapping evaluation, we also contribute a coral reef surveying dataset with synchronized multi-modality data. Extensive experiments on public and our proposed benchmarks demonstrate that APVI-SLAM achieves state-of-the-art localization and reconstruction quality at real-time speeds.

Problem

• underwater SLAM
• visual-inertial localization
• multi-sensor fusion
• photorealistic mapping
• extreme subsea environments

Innovation

• reliability-aware fusion
• sliding-window freezing
• quadtree-guided mapping
• underwater photorealistic reconstruction
• multi-sensor SLAM