零参考样本下的逆光图像深度学习增强方法  

Deep learning based backlight image enhancement method derived of zero-reference samples

作　　者：王知音 张二虎 石争浩[2] 段敬红[2] Wang Zhiyin;Zhang Erhu;Shi Zhenghao;Duan Jinghong(Faculty of Printing,Packaging and Digital Media,Xi′an University of Technology,Xi′an 710048,China;School of Computer Science and Engineering,Xi′an University of Technology,Xi′an 710048,China)

机构地区：[1]西安理工大学印刷包装与数字媒体学院,西安710048 [2]西安理工大学计算机科学与工程学院,西安710048

出　　处：《中国图象图形学报》2022年第5期1589-1603,共15页Journal of Image and Graphics

基　　金：陕西省重点研发计划资助(2022GY-274);陕西省教育厅协同创新中心项目(20JY053)。

摘　　要：目的随着数码设备的普及,拍照成为记录生活的一种主流方式。但是周围环境的不可控因素会导致用户获取到逆光图像。传统的图像增强方法大多是全局增强,通常存在增强过度或增强程度不够的问题。而基于深度学习的图像增强方法大多是针对低照度图像增强任务,此类方法无法同时兼顾逆光图像中欠曝光区域和过曝光区域的增强问题,且在网络训练时需要成对的数据集。方法提出一个基于注意力机制的逆光图像增强网络ABIEN(attention-based backlight image enhancement network),该网络学习逆光图像与增强图像之间像素级的映射参数,解决无参考图像的问题,同时使用注意力机制使网络关注欠曝光区域和过曝光区域的增强。为了解决无法获取成对图像数据集的问题,所设计的网络学习逆光图像与恢复图像之间的映射参数,并借助该参数进行迭代映射以实现图像增强;为了在增强欠曝光区域的同时还能抑制过曝光区域增强过度的问题,通过引入注意力机制帮助网络关注这两个不同区域的增强过程;为了解决大多数图像恢复中都会出现的光晕、伪影等问题,采用原始分辨率保留策略,在不改变图像大小的情况下将主网络各个深度的特征信息充分利用,以削弱该类问题对增强图像的影响。结果通过将本文方法与MSRCR(multi-scale retinex with color restoration)、Fusion-based(fusion-based method)、Learnning-based(learning-based restoration)、NPEA(naturalness preserved enhancement algorithm)和Ex CNet(exposure correction network)等方法进行对比,本文方法得到的增强图像从主观上看曝光度更好、颜色保留更真实、伪影更少;从客观指标来看,本文方法在LOE(lightness order error)上取得了最好的效果,在VLD(visibility level descriptor)和CDIQA(contrast-distorted image quality assessment)上表现也很好;从处理时间上来看,本文方法的处理时间相对较短,ObjectiveDigital photos have been evolved in human life.However,backlight images are captured due to its unidentified factors in the context of its scenarios.Without careful control of lighting,important objects can disappear in the backlight areas,causing backlight images to become a fatal problem of image quality degradation.The theoretical cause of backlight image is that the object being photographed is located right between the light source and the shooting lens,the overall dynamic range of the light in the same picture is extremely large.Due to the limitation of the photosensitive element,the general camera cannot incorporate all the levels of detail into the latitude range,resulting in poor shooting results,which further causes problems such as barren visual quality of the entire image,color degradation of meaningful areas and loss of detail information in the image.Current image enhancement methods are focused on the aspect of global enhancement,and there is an issue of excessive enhancement or insufficient enhancement for backlight images.Moreover,deep learning based image enhancement method is mainly related to the low-illumination image enhancement task,which cannot take the backlight images enhancement of underexposed and overexposed regions into account simultaneously.We illustrate an attention-based backlight image enhancement network(ABIEN),which can resolve non-pairing image sets via learning the pixel-wise mapping relationship between the backlight image and the enhanced image,and facilitate network training to enhance underexposed and overexposed regions.MethodFirst,our demonstrated network is designated to learn the mapping parameters between the backlight image and the restored image to obtain paired datasets in an iterative way,and the enhanced image is obtained based on learned mapping parameters to transform the backlight image.Pixel-level parameters avoid the disadvantages of the previous methods without distinction enhancement and achieve targeted enhancement.Next,in order to enhance the

关 键 词：逆光图像 图像增强 卷积神经网络(CNN) 注意力机制 零参考样本 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]