Hole-filling framework by combining structural and textural information for the 3D Terracotta Warriors

被引:3
作者
Chu, Tong [1 ]
Yao, Wenmin [1 ]
Liu, Jie [1 ]
Xu, Xueli [1 ]
Nan, Haiyang [1 ]
Cao, Xin [1 ]
Li, Kang [1 ]
Zhou, Mingquan [1 ]
机构
[1] Northwest Univ, Sch Informat & Technol, Natl Local Joint Engn Res Ctr Cultural Heritage D, Xian, Peoples R China
关键词
hole completion; Terracotta Warriors; neural network; point cloud; cultural relic restoration; CULTURAL-HERITAGE; POINT; SHAPE;
D O I
10.1117/1.JRS.15.046503
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
As one of the eight wonders in the world, the virtual restoration of Terracotta Warriors is of great significance to archaeology. However, some parts of fragments were corroded for thousands of years, resulting in the existence of several holes in most of the restored cultural heritage artifacts. Based on the structural and textural information, we present a framework for filling the hole. First, a method based on the Poisson equation was employed to fill the hole on the triangular mesh model. Then, to complete the surface color and texture information of the three-dimension (3D) model, make the hole patch, and the original model surface texture natural transition, the 3D problem is converted into two-dimension (2D) image inpaint problem, and a refined network is added into EdgeConnect to generate a higher resolution result. A set of experiments is performed to evaluate the performance of our proposed framework. We hope the proposed framework can provide a useful tool to guide the virtual restoration of other cultural heritage artifacts. (C) 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)
引用
收藏
页数:18
相关论文
共 55 条
[41]   VConv-DAE: Deep Volumetric Shape Learning Without Object Labels [J].
Sharma, Abhishek ;
Grau, Oliver ;
Fritz, Mario .
COMPUTER VISION - ECCV 2016 WORKSHOPS, PT III, 2016, 9915 :236-250
[42]  
Hoang VD, 2013, IEEE IND ELEC, P5498, DOI 10.1109/IECON.2013.6700032
[43]  
Varley J, 2017, IEEE INT C INT ROBOT, P2442, DOI 10.1109/IROS.2017.8206060
[44]  
Wang F., 2017, Int. J. Eng. Tech. Res., V7, P41
[45]  
Wang J, 2003, 2003 INTERNATIONAL CONFERENCE ON GEOMETRIC MODELING AND GRAPHICS, PROCEEDINGS, P201
[46]   High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs [J].
Wang, Ting-Chun ;
Liu, Ming-Yu ;
Zhu, Jun-Yan ;
Tao, Andrew ;
Kautz, Jan ;
Catanzaro, Bryan .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :8798-8807
[47]   Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks [J].
Wang, Weiyue ;
Huang, Qiangui ;
You, Suya ;
Yang, Chao ;
Neumann, Ulrich .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2317-2325
[48]   Image quality assessment: From error visibility to structural similarity [J].
Wang, Z ;
Bovik, AC ;
Sheikh, HR ;
Simoncelli, EP .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (04) :600-612
[49]  
WU Z, 1985, MUSEUM, V37, P140
[50]   3D Object Reconstruction from a Single Depth View with Adversarial Learning [J].
Yang, Bo ;
Wen, Hongkai ;
Wang, Sen ;
Clark, Ronald ;
Markham, Andrew ;
Trigoni, Niki .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, :679-688