Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar

TL;DR

This paper introduces a neural rendering-based analysis-by-synthesis optimization for coherent synthetic aperture sonar imaging, improving image quality by incorporating physics constraints and scene priors, validated through simulations and experiments.

Contribution

It presents a novel neural rendering approach for SAS image reconstruction that integrates physics-based constraints and scene priors, enhancing image quality over existing methods.

Findings

Produces superior reconstructions in simulation and real data

Effectively incorporates physics constraints and scene priors

Validated on both air and water datasets

Abstract

Synthetic aperture sonar (SAS) measures a scene from multiple views in order to increase the resolution of reconstructed imagery. Image reconstruction methods for SAS coherently combine measurements to focus acoustic energy onto the scene. However, image formation is typically under-constrained due to a limited number of measurements and bandlimited hardware, which limits the capabilities of existing reconstruction methods. To help meet these challenges, we design an analysis-by-synthesis optimization that leverages recent advances in neural rendering to perform coherent SAS imaging. Our optimization enables us to incorporate physics-based constraints and scene priors into the image formation process. We validate our method on simulation and experimental results captured in both air and water. We demonstrate both quantitatively and qualitatively that our method typically produces superior reconstructions than existing approaches. We share code and data for reproducibility.