UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing

TL;DR

UWGAN introduces an unsupervised GAN-based approach for real-world underwater image color restoration and dehazing, achieving high-speed processing and maintaining scene structure, improving visibility for underwater exploration.

Contribution

The paper presents a novel unsupervised GAN model with an efficient U-Net for underwater image restoration, trained on synthetic data, and capable of real-time processing.

Findings

Outperforms existing methods qualitatively and quantitatively.

Achieves up to 125FPS on NVIDIA 1060 GPU.

Demonstrates effective real-world underwater image enhancement.

Abstract

In real-world underwater environment, exploration of seabed resources, underwater archaeology, and underwater fishing rely on a variety of sensors, vision sensor is the most important one due to its high information content, non-intrusive, and passive nature. However, wavelength-dependent light attenuation and back-scattering result in color distortion and haze effect, which degrade the visibility of images. To address this problem, firstly, we proposed an unsupervised generative adversarial network (GAN) for generating realistic underwater images (color distortion and haze effect) from in-air image and depth map pairs based on improved underwater imaging model. Secondly, U-Net, which is trained efficiently using synthetic underwater dataset, is adopted for color restoration and dehazing. Our model directly reconstructs underwater clear images using end-to-end autoencoder networks, while maintaining scene content structural similarity. The results obtained by our method were compared with existing methods qualitatively and quantitatively. Experimental results obtained by the proposed model demonstrate well performance on open real-world underwater datasets, and the processing speed can reach up to 125FPS running on one NVIDIA 1060 GPU. Source code, sample datasets are made publicly available at https://github.com/infrontofme/UWGAN_UIE.