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

12/21/2019
by   Nan Wang, et al.
0

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.

READ FULL TEXT
research
07/10/2018

Deep Underwater Image Enhancement

In an underwater scene, wavelength-dependent light absorption and scatte...
research
02/23/2017

WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images

This paper reports on WaterGAN, a generative adversarial network (GAN) f...
research
12/18/2022

SUCRe: Leveraging Scene Structure for Underwater Color Restoration

Underwater images are altered by the physical characteristics of the med...
research
11/27/2022

Towards Realistic Underwater Dataset Generation and Color Restoration

Recovery of true color from underwater images is an ill-posed problem. T...
research
05/22/2019

Underwater Color Restoration Using U-Net Denoising Autoencoder

Visual inspection of underwater structures by vehicles, e.g. remotely op...
research
07/06/2021

HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration

Robust vision restoration for an underwater image remains a challenging ...
research
01/11/2018

Enhancing Underwater Imagery using Generative Adversarial Networks

Autonomous underwater vehicles (AUVs) rely on a variety of sensors - aco...

Please sign up or login with your details

Forgot password? Click here to reset