DichroGAN: Towards Restoration of in-air Colours of Seafloor from Satellite Imagery

TL;DR

DichroGAN is a novel conditional GAN framework that restores in-air seafloor colours from satellite images by modeling light absorption and scattering, trained on satellite data, and outperforming existing methods.

Contribution

The paper introduces DichroGAN, a two-step cGAN approach for underwater colour restoration from satellite imagery, combining spectral and transmission estimations for improved accuracy.

Findings

Achieves competitive performance with state-of-the-art methods

Effectively models underwater light absorption and scattering

Demonstrates robustness on satellite and underwater datasets

Abstract

Recovering the in-air colours of seafloor from satellite imagery is a challenging task due to the exponential attenuation of light with depth in the water column. In this study, we present DichroGAN, a conditional generative adversarial network (cGAN) designed for this purpose. DichroGAN employs a two-steps simultaneous training: first, two generators utilise a hyperspectral image cube to estimate diffuse and specular reflections, thereby obtaining atmospheric scene radiance. Next, a third generator receives as input the generated scene radiance containing the features of each spectral band, while a fourth generator estimates the underwater light transmission. These generators work together to remove the effects of light absorption and scattering, restoring the in-air colours of seafloor based on the underwater image formation equation. DichroGAN is trained on a compact dataset derived from PRISMA satellite imagery, comprising RGB images paired with their corresponding spectral bands and masks. Extensive experiments on both satellite and underwater datasets demonstrate that DichroGAN achieves competitive performance compared to state-of-the-art underwater restoration techniques.