R2D2-GAN: Unlimited Resolution Image Generation for Acoustic Data

摘要

In this paper, we present a novel simulation technique for generating high-quality images of any predefined resolution. This method can be used to synthesize sonar scans of size equivalent to those collected during a full-length mission, with across-track resolutions of any chosen magnitude. In essence, our model extends generative adversarial network (GAN)-based architecture into a conditional recursive setting that facilitates the continuity of the generated images. The data produced are continuous and realistically looking and can also be generated at least two times faster than the real speed of acquisition for the sonars with higher resolutions, such as EdgeTech. The seabed topography can be fully controlled by the user. The visual assessment tests demonstrate that humans cannot distinguish the simulated images from real ones. Moreover, experimental results suggest that, in the absence of real data, the autonomous recognition systems can benefit greatly from training with the synthetic data, produced by the double-recursive double-discriminator GANs (R2D2-GANs).