Towards Real-Time Advancement of Underwater Visual Quality with GAN

TL;DR

This paper introduces a real-time GAN-based method for underwater image enhancement that preserves content, suppresses noise, and adapts to underwater properties, demonstrated through extensive tests and real-world seabed experiments.

Contribution

It proposes a novel multi-branch discriminator GAN architecture with a dark channel prior loss and underwater index-based critic for improved underwater image restoration.

Findings

Outperforms existing methods in visual quality and feature restoration

Achieves real-time adaptive underwater image enhancement

Validated through real-world seabed experiments

Abstract

Low visual quality has prevented underwater robotic vision from a wide range of applications. Although several algorithms have been developed, real-time and adaptive methods are deficient for real-world tasks. In this paper, we address this difficulty based on generative adversarial networks (GAN), and propose a GAN-based restoration scheme (GAN-RS). In particular, we develop a multi-branch discriminator including an adversarial branch and a critic branch for the purpose of simultaneously preserving image content and removing underwater noise. In addition to adversarial learning, a novel dark channel prior loss also promotes the generator to produce realistic vision. More specifically, an underwater index is investigated to describe underwater properties, and a loss function based on the underwater index is designed to train the critic branch for underwater noise suppression. Through extensive comparisons on visual quality and feature restoration, we confirm the superiority of the proposed approach. Consequently, the GAN-RS can adaptively improve underwater visual quality in real time and induce an overall superior restoration performance. Finally, a real-world experiment is conducted on the seabed for grasping marine products, and the results are quite promising. The source code is publicly available at https://github.com/SeanChenxy/GAN_RS.