文献类型：期刊文献

中文题名：基于Retinex-UNet算法的低照度图像增强

英文题名：Low Illumination Image Enhancement Based on Retinex-UNet Algorithm

作者：刘佳敏[1];何宁[1];尹晓杰[1]

第一作者：刘佳敏

机构：[1]北京联合大学智慧城市学院,北京100101

第一机构：北京联合大学智慧城市学院

年份：2020

卷号：56

期号：22

起止页码：211-216

中文期刊名：计算机工程与应用

外文期刊名：Computer Engineering and Applications

收录：CSTPCD;;北大核心:【北大核心2017】；CSCD:【CSCD_E2019_2020】；

基金：国家自然科学基金(No.61572077,No.61872042);北京市自然科学基金委和北京市教委联合重点项目(No.KZ201911417048);北京市教委科技计划项目(No.KM201811417004)。

语种：中文

中文关键词：Retinex-Net;低照度图像;卷积神经网络;U-Net;RUNet

外文关键词：Retinex-Net;low illumination image;convolutional neural network;U-Net;RUNet

摘要：针对Retinex应用于多种场景时,其约束和参数会受到模型容量限制的问题,提出了一种基于深度学习的低照度图像增强算法,并构建了新的网络架构Retinex-UNet(RUNet)。该架构包含图像分解网络与图像增强网络两部分,利用Retinex-Net网络思想,通过卷积神经网络(Convolutional Neural Network,CNN)学习并分解图像,将其结果作为增强网络的输入,对输入图像进行端对端训练。在增强网络中构建了基于U-Net的网络架构,其可对任意大小的图像进行增强。通过在公开数据集(LOL,SID)上验证表明,RUNet方法在效果上有所改进,尤其是整体视觉效果。
When Retinex is applied to many scenarios,its constraints and parameters are limited by the model capacity.A low illumination image enhancement algorithm based on deep learning is proposed,and a new network architecture Retinex-UNet(RUNet)is constructed.The architecture includes image decomposition network and image enhancement network.Firstly,the Retinex-Net idea is adopted.The Convolutional Neural Network(CNN)is used to learn and decompose the image,and then the result is used as an input to the enhanced network to perform end-to-end training on the input image.The enhanced network builds a U-Net-based network architecture that enhances images of any size.Validation on public data sets(LOL,SID)shows that the RUNet method has improved in performance,especially the overall visual effect.