RUIG: Realistic Underwater Image Generation Towards Restoration

In this paper, we present a novel method for generating synthetic underwater images considering revised image formation model. We propose to use the generated synthetic underwater images to train a conditional generative adversarial network (CGAN) towards restoration of degraded underwater images. Restoration of degraded underwater images using traditional dehazing models is challenging as they are insensitive to wavelength, depth, water type and treat backscattering and direct signal attenuation coefficients to be equal. However, learning based models for restoration perform well but sensitive to availability of ground truth information. Generating ground truth labels in underwater scenario demands in-situ measurements using expensive equipments and is infeasible due to varying underwater currents. Towards this, we propose to generate synthetic underwater images using revised image formation model. Revised image formation model is sensitive to different attenuation coefficients: 1) back scattering, 2) direct scattering and 3) veiling light. We propose to estimate these attenuation coefficients considering proven facts from the literature. We demonstrate restoration of real underwater images through restoration framework trained using rendered synthetic underwater images, and compare results of restoration with state-of-the-art techniques.

Automated summary

In this paper, a novel method for generating synthetic underwater images using a revised image formation model is proposed. The synthetic images are then used to train a CGAN for restoring degraded underwater images. Traditional dehazing models are challenging for underwater image restoration, while learning-based models are sensitive to the availability of ground truth information. The proposed revised image formation model, which considers different attenuation coefficients, offers a more accurate representation of underwater scenarios.