Neural Shape-from-Shading for Survey-Scale Self-Consistent Bathymetry from Sidescan

TL;DR

This paper introduces a neural network-based method to generate high-quality, survey-scale bathymetry from multiple sidescan sonar lines, leveraging neural representations to improve accuracy and scalability over previous single-line approaches.

Contribution

The paper presents a novel neural shape-from-shading approach using sinusoidal representation networks to produce consistent bathymetry from multiple sidescan lines at survey scale.

Findings

Achieves high-quality bathymetry comparable to multibeam data.

Scalable approach demonstrated on large sidescan surveys.

Improves consistency by integrating multiple observations.

Abstract

Sidescan sonar is a small and cost-effective sensing solution that can be easily mounted on most vessels. Historically, it has been used to produce high-definition images that experts may use to identify targets on the seafloor or in the water column. While solutions have been proposed to produce bathymetry solely from sidescan, or in conjunction with multibeam, they have had limited impact. This is partly a result of mostly being limited to single sidescan lines. In this paper, we propose a modern, salable solution to create high quality survey-scale bathymetry from many sidescan lines. By incorporating multiple observations of the same place, results can be improved as the estimates reinforce each other. Our method is based on sinusoidal representation networks, a recent advance in neural representation learning. We demonstrate the scalability of the approach by producing bathymetry from a large sidescan survey. The resulting quality is demonstrated by comparing to data collected with a high-precision multibeam sensor.