Back in time:digital restoration techniques for the millennium Dunhuang murals

作     者：Tao Yifeng Song Yucheng Xu Mengqiu Zhang Chuang Wu Ming Bai Sule Tao Yifeng;Song Yucheng;Xu Mengqiu;Zhang Chuang;Wu Ming;Bai Sule

作者机构：School of Artificial IntelligenceBeijing University of Posts and TelecommunicationsBeijing 100876China School of Computer Science(National Pilot Software Engineering School)Beijing University of Posts and TelecommunicationsBeijing 100876China 

出 版 物：《The Journal of China Universities of Posts and Telecommunications》 (中国邮电高校学报（英文版）)

年 卷 期：2022年第29卷第2期

页      面：13-23页

核心收录：

学科分类：1304[艺术学-美术学] 0601[历史学-考古学] 13[艺术学] 060107[历史学-文化遗产与博物馆] 06[历史学] 060109[历史学-专门考古] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the Ministry of Education-China Mobile Communications (MCM20190701) 

主　　题：image inpainting image enhancement mural restoration 

摘      要：In the long history of more than 1 500 years,Dunhuang murals suffered from various deteriorations causing irreversible damage such as falling off,fading,and so ***,the existing Dunhuang mural restoration methods are time-consuming and not feasible to facilitate cultural dissemination and permanent *** by cultural computing using artificial intelligence,gated-convolution-based dehaze net(GD-Net) was proposed for Dunhuang mural refurbishment and comprehensive ***,a neural network with gated convolution was applied to restore the falling off areas of the mural to ensure the integrity of the mural ***,a dehaze network was applied to enhance image quality to cope with the fading of the ***,a Dunhuang mural dataset was presented to meet the needs of deep learning approach,containing 1 180 images from the Cave 290 and Cave 112 of the Mogao *** experimental results demonstrate the effectiveness and superiority of GD-Net.