激光与光电子学进展, 2020, 57 (14): 141002, 网络出版: 2020-07-23
基于条件生成对抗网络的水下图像增强 下载: 1535次
Underwater Image Enhancement Based on Conditional Generative Adversarial Network
图像处理 水下图像 颜色退化 条件生成对抗网络 深度学习 image processing underwater image color degradation conditional generative adversarial networks deep learning
摘要
为提升不同颜色水下图像的增强效果,提出一种基于条件生成对抗网络的水下图像增强方法。该网络在生成模型中加入残差密集块中的残差模块,其密集级联和残差连接可以提取图像的特征信息,改善梯度消失现象;在目标函数中增加两种新的损失函数建立网络模型,使得增强后的图像与输入图像的内容和结构保持一致。实验结果表明,所提方法对不同颜色水下图像的增强效果优于现有算法,具有更好的视觉效果。
Abstract
This study proposes a conditional generative adversarial network that improves the performance of underwater image enhancement of different colors. The network adds residual module in residual dense blocks into the generative model, and its dense cascade and residual connections extract image features and ease the gradient disappearance problem. By adding two new loss functions to the objective function, a new network model is established which can make the content and structure of the enhanced images be consistent with that of the input images. The experimental results show that the proposed method has better enhancement performance and visual effect than existing algorithms.
晋玮佩, 郭继昌, 祁清. 基于条件生成对抗网络的水下图像增强[J]. 激光与光电子学进展, 2020, 57(14): 141002. Weipei Jin, Jichang Guo, Qing Qi. Underwater Image Enhancement Based on Conditional Generative Adversarial Network[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141002.