结合深度学习的雕像面部数字复原方法  

Digital Restoration Method of Sculpture Face Based on Deep Learning

作　　者：朱夫宏 李彩林[1,2] 郭宝云 王志勇[1] 廖祥灿[1] Zhu Fuhong;Li Cailin;Guo Baoyun;Wang Zhiyong;Liao Xiangcan(School of Civil and Architectural Engineering,Shandong University of Technology,Zibo,Shandong 255049,China;Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions,Ministry of Education,Henan University,Kaifeng,Henan 475001,China)

机构地区：[1]山东理工大学建筑工程学院,山东淄博255049 [2]河南大学黄河中下游数字地理技术教育部重点实验室,河南开封475001

出　　处：《激光与光电子学进展》2022年第4期321-328,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41601496,61572444);自然资源部大湾区地理环境监测重点实验室(深圳大学)开放基金(SZU51029202003);黄河中下游数字地理技术教育部重点实验室(河南大学)开放基金(GTYR202004);山东省艺术科学重点课题(ZD202008267,201806353)。

摘　　要：针对面部破损的雕像在实际复原过程中容易遭受二次损坏,以及雕像历史影像数据匮乏的问题,提出一种基于深度学习网络,利用单张雕像面部影像实现雕像破损面部数字复原的方法。首先利用深度学习网络对雕像未破损前的单张影像数据进行处理,生成点云,然后通过激光扫描仪获取破损后的雕像点云,最后对两者数据进行配准融合,生成完整的雕像模型,从而实现雕像面部数字复原。对完好雕像扫描生成的点云进行人为破坏,以模拟面部破损雕像,并利用所提方法进行复原。实验结果表明,所提方法能够有效实现面部破损雕像的数字复原,且生成的雕像模型面部细节准确,复原精度较高。The damaged faces of statues are prone to getting redamaged during the restoration process, and the historical image data of statues are insufficient. To solve these problems, we propose a digital restoration method based on a deep learning network, which can use a single statue face image to restore the damaged face of the statue.First, the deep learning network is used to process the single image data of the undamaged statue to generate a point cloud. Second, the damaged statue point cloud is obtained through a laser scanner. Finally, the two data are registered and fused to generate a complete statue model to realize the digital restoration of the statue face. In this study, the artificially damaged point cloud of undamaged facial statues is used to simulate the damaged facial statues,and the proposed method is used for restoration. The experimental results show that the proposed method can effectively realize the digital restoration of facial damaged statues, and the generated statue model has correct facial details and high restoration accuracy.

关 键 词：机器视觉 数字图像处理 深度学习 三维重建 面部破损雕像 数字复原 

分 类 号：P232[天文地球—摄影测量与遥感]