基于深度学习的图像补全算法综述  

Survey of Image Inpainting Algorithms Based on Deep Learning

作　　者：唐浩丰 董元方[1] 张依桐 孙娟娟 TANG Hao-feng;DONG Yuan-fang;ZHANG Yi-tong;SUN Juan-juan(School of Economic and Management,Changchun University of Science and Technology,Changchun 130022,China)

机构地区：[1]长春理工大学经济管理学院,长春130022

出　　处：《计算机科学》2020年第S02期151-164,共14页Computer Science

基　　金：吉林省自然科学基金(20150101053JC)。

摘　　要：图像补全是图像处理的一个研究领域,为有物体遮挡以及图像关键部分缺失状况下的图像识别提供了解决方案,应用领域非常广泛,受到了人们的关注。经深度学习方法补全的图像具有更高的图像分辨率和可靠性,逐渐成为图像补全的主流方法之一。文中针对图像补全领域的主要问题,介绍了相关深度学习方法的基本原理和经典算法,系统而渐进地剖析了2010年以来有代表性的图像补全方法,探讨了基于深度学习的图像补全在不同领域的具体应用,并列举了该研究领域目前面临的几个问题。Image inpainting is a research field of image processing that provides solutions for image recognition in the presence of object occlusion and in the absence of critical parts of the image,attracts widespread attention in a wide range of fields.Image inpainted by deep learning methods have higher image resolution and reliability,which makes deep learning one of the mainstream methods of image inpainting.This paper introduces the basic principles and classical algorithms of the relevant deep learning methods,systematically and progressively dissects the representative image inpainting methods since 2010,explores the specific applications of deep learning-based image inpainting in different fields,and lists several research problems faced by this research field currently.

关 键 词：图像补全 深度学习 生成对抗网络 上下文编码 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]