基于生成对抗网络的图像阴影消除算法  

Image Shadow Removal Algorithm Based on Generative Adversarial Network

作　　者：石恒 张玲 SHI Heng;ZHANG Ling(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,武汉430065

出　　处：《计算机科学》2021年第6期145-152,共8页Computer Science

基　　金：国家自然科学基金(61902286)。

摘　　要：虽然现有基于深度学习的图像阴影消除方法已取得了一定的进步,但是这些方法主要关注图像本身,没有很好地探索其他额外与阴影相关的信息,因此这些方法常常存在图像纹理模糊、内容不协调等问题。针对这些问题,文中基于生成对抗网络(Generative Adversarial Network, GAN),提出了一种新的阴影消除网络模型。该方法首先从全局上生成一个粗糙的阴影消除结果,再利用与阴影相关的残差信息对粗糙的结果在颜色和细节上进行局部优化,从而获得更加真实自然的无阴影图像。生成网络包含3个编码-解码结构,首先利用第1个编码-解码结构对阴影图像进行整体光照恢复,生成一个初始的阴影消除结果;同时将与阴影相关的残差信息作为辅助信息输入第2个编码-解码器,对初始结果进行进一步优化;为了避免阴影区域出现纹理不协调等问题,最后利用第3个编码-解码器对阴影区域细节纹理进行修正,使得生成的阴影消除图像更加真实自然。对抗网络由Patch鉴别器构成,用来鉴别图像阴影消除结果的真实性。实验结果表明,与目前的图像阴影消除方法相比,无论在阴影区域还是在非阴影区域上所提方法都达到了最佳的RMSE值,且该方法生成的阴影消除图像与真实无阴影图像更加接近,有效解决了纹理模糊等问题,证实了该方法的有效性和可行性。Although the existing learning-based shadow removal methods have made some progress,these methods mainly focus on the image itself and do not well explore other information related to shadow.These methods often result in problems such as image texture blurring or illumination inconsistency.To solve these problems,this paper proposes a new network based on genera-tive adversarial network(GAN)to remove shadows in the image.First,it uses an encoder-decoder to obtain a coarse shadow removal result.Then,it optimizes the coarse result by utilizing the shadow-related residual information to produce more realistic and natural shadow removal image.Our generator contains three encoder-decoder structures.The first encoder-decoder is used to restore the illumination of the image and generate a coarse shadow removal result.To solve the problem of color and illumination inconsistency,the residual information is input into the following encoder-decoder to correct the coarse results.Furthermore,the third encoder-decoder is used to refine the details in the image,which can avoid texture inconsistency between shadow regions and nonshadow regions.The discriminator is used to identify the authenticity of the image shadow removal result.Experiments show that the proposed method achieves the best RMSE value in both shaded region and non-shaded region,and effectively solves the problem of texture blur.In addition,the shadow removal image generated by the proposed method is much closer to the real image,which proves the effectiveness and feasibility of the proposed method.

关 键 词：阴影消除 生成对抗网络 残差信息 编码-解码结构 Patch鉴别器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]