[论文解读] Towards Quality Advancement of Underwater Machine Vision with Generative Adversarial Networks

Xingyu Chen, Junzhi Yu+4 more|arXiv (Cornell University)|Dec 3, 2017

Image Enhancement Techniques被引用 7

一句话总结

本文提出两种实时、自适应的水下图像增强方法——基于滤波的增强方案（FRS）和基于生成对抗网络的增强方案（GAN-RS）——分别采用傅里叶域滤波和一种新型生成对抗网络架构，结合水下指数损失与暗通道先验损失。GAN-RS 在色彩校正、对比度增强、去雾化和特征恢复方面达到当前最优性能，在图像质量与处理速度上均优于现有方法。

ABSTRACT

Underwater machine vision has attracted significant attention, but its low quality has prevented it from a wide range of applications. Although many different algorithms have been developed to solve this problem, real-time adaptive methods are frequently deficient. In this paper, based on filtering and the use of generative adversarial networks (GANs), two approaches are proposed for the aforementioned issue, i.e., a filtering-based restoration scheme (FRS) and a GAN-based restoration scheme (GAN-RS). Distinct from previous methods, FRS restores underwater images in the Fourier domain, which is composed of a parameter search, filtering, and enhancement. Aiming to further improve the image quality, GAN-RS can adaptively restore underwater machine vision in real time without the need for pretreatment. In particular, information in the Lab color space and the dark channel is developed as loss functions, namely, underwater index loss and dark channel prior loss, respectively. More specifically, learning from the underwater index, the discriminator is equipped with a carefully crafted underwater branch to predict the underwater probability of an image. A multi-stage loss strategy is then developed to guarantee the effective training of GANs. Through extensive comparisons on the image quality and applications, the superiority of the proposed approaches is confirmed. Consequently, the GAN-RS is considerably faster and achieves a state-of-the-art performance in terms of the color correction, contrast stretch, dehazing, and feature restoration of various underwater scenes. The source code will be made available.

研究动机与目标

• 为解决水下机器视觉图像质量低下所导致的实际应用受限这一长期挑战。
• 开发实时、自适应的图像增强技术，以克服现有非自适应或非实时方法的局限性。
• 通过提升色彩保真度、对比度与特征清晰度，改善水下场景的图像质量。
• 提出一种专为水下图像增强设计的新型生成对抗网络架构，并配备定制化损失函数。
• 通过快速推理与极少预处理步骤，实现实际部署的可行性。

提出的方法

• FRS 通过参数搜索、滤波与增强三个阶段，在傅里叶域中实现水下图像的恢复。
• GAN-RS 采用生成对抗网络框架，结合水下指数损失与暗通道先验损失的多阶段损失策略。
• 判别器包含一个专用的水下分支，用于预测图像是否为水下图像。
• 利用 Lab 色彩空间信息与暗通道先验作为监督信号，引导生成器学习。
• 该方法端到端运行，无需任何预处理步骤，实现实时处理。
• 精心设计的损失函数融合感知先验与物理先验，以提升恢复结果的保真度。

实验结果

研究问题

• RQ1 基于傅里叶域滤波的方法能否在保证实时性能的前提下实现有效的水下图像增强？
• RQ2 如何对生成对抗网络进行改进，使其在先验知识极少且推理速度要求高的情况下实现水下图像恢复？
• RQ3 水下指数损失与暗通道先验损失在多大程度上能提升色彩校正与对比度增强效果？
• RQ4 多阶段损失策略是否能有效稳定生成对抗网络在水下图像增强任务中的训练过程？
• RQ5 与当前最优技术相比，所提方法在视觉质量与计算效率方面表现如何？

主要发现

• GAN-RS 在多种水下场景中，于色彩校正、对比度拉伸、去雾化与特征恢复方面均达到当前最优性能。
• 所提方法在定量图像质量指标与视觉保真度方面，显著优于现有技术。
• GAN-RS 展现出卓越的实时性能，可支持在动态水下应用中的实际部署。
• 水下指数损失与暗通道先验损失的融合，实现了更自然的色彩还原与更优的对比度表现。
• 多阶段损失策略有效稳定了生成对抗网络的训练过程，并提升了图像恢复质量。
• 源代码将公开发布，以支持结果复现与后续研究。