Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

TL;DR

This paper introduces SAS GAN, a novel pipeline combining optical rendering and GANs to generate realistic synthetic SAS images, addressing data scarcity and bias in sonar imaging for underwater exploration.

Contribution

The paper presents a new method coupling optical rendering with GANs to produce controllable, realistic synthetic SAS images, improving dataset augmentation for sonar applications.

Findings

Generated images are qualitatively realistic.

Quantitative metrics show improved dataset augmentation.

Method enables control over image geometry and parameters.

Abstract

Acquisition of Synthetic Aperture Sonar (SAS) datasets is bottlenecked by the costly deployment of SAS imaging systems, and even when data acquisition is possible,the data is often skewed towards containing barren seafloor rather than objects of interest. We present a novel pipeline, called SAS GAN, which couples an optical renderer with a generative adversarial network (GAN) to synthesize realistic SAS images of targets on the seafloor. This coupling enables high levels of SAS image realism while enabling control over image geometry and parameters. We demonstrate qualitative results by presenting examples of images created with our pipeline. We also present quantitative results through the use of t-SNE and the Fr\'echet Inception Distance to argue that our generated SAS imagery potentially augments SAS datasets more effectively than an off-the-shelf GAN.