We present a technique for dense 3D reconstruction of objects using an imaging sonar, also known as forward-looking sonar (FLS). Compared to previous methods that model the scene geometry as point clouds or volumetric grids, we represent the geometry as a neural implicit function. Additionally, given such a representation, we use a differentiable volumetric renderer that models the propagation of acoustic waves to synthesize imaging sonar measurements. We perform experiments on real and synthetic datasets and show that our algorithm reconstructs high-fidelity surface geometry from multi-view FLS images at much higher quality than was possible with previous techniques and without suffering from their associated memory overhead.
@article{arxiv.2209.08221,
title = {Neural Implicit Surface Reconstruction using Imaging Sonar},
author = {Mohamad Qadri and Michael Kaess and Ioannis Gkioulekas},
journal= {arXiv preprint arXiv:2209.08221},
year = {2022}
}