TY - JOUR
KW - Data handling
KW - Intangible cultural heritages
KW - 3D models
KW - Three dimensional computer graphics
KW - Image reconstruction
KW - Three dimensional displays
KW - Display system
KW - Generative adversarial networks
KW - High resolution
KW - Optical resolving power
KW - Processing modules
KW - Quadratic programming
KW - System functions
KW - Three-dimensional display
AU - Jiachun Wang
AU - Junkui Song
AU - Yizhe Zhang
AU - Hao Chen
AB - This paper designs a three-dimensional display system for intangible cultural heritage based on generative adversarial networks. The system function is realized through four modules: input module, data processing module, 3D model generation module, and model output module. Two 3D model reconstruction methods are used to realize the transformation from 2D images to 3D models. In the low-resolution Nuo surface 3D construction, multiresidual dense blocks are introduced and applied to the deep image super-resolution network. The experimental comparison results show that the quadratic optimization multifusion 3D construction model proposed in this paper can achieve considerable improvement and can improve the reconstruction accuracy by about 6.3\%. In the high-resolution 3D construction of the Nuo surface, a generative adversarial network model is used to improve the generator, discriminator, and loss function of the original SRGAN model. Experimental results show that this method can generate super-resolution images with more realistic and natural depth maps. In addition, when it is used for high-resolution 3D Nuo surface sculpting, it can also generate 3D voxel Nuo surfaces with more details.
BT - Scientific Programming
DA - jul
DO - 10.1155/2022/2944750
LA - English
N1 - Publisher: Hindawi Limited
N2 - This paper designs a three-dimensional display system for intangible cultural heritage based on generative adversarial networks. The system function is realized through four modules: input module, data processing module, 3D model generation module, and model output module. Two 3D model reconstruction methods are used to realize the transformation from 2D images to 3D models. In the low-resolution Nuo surface 3D construction, multiresidual dense blocks are introduced and applied to the deep image super-resolution network. The experimental comparison results show that the quadratic optimization multifusion 3D construction model proposed in this paper can achieve considerable improvement and can improve the reconstruction accuracy by about 6.3\%. In the high-resolution 3D construction of the Nuo surface, a generative adversarial network model is used to improve the generator, discriminator, and loss function of the original SRGAN model. Experimental results show that this method can generate super-resolution images with more realistic and natural depth maps. In addition, when it is used for high-resolution 3D Nuo surface sculpting, it can also generate 3D voxel Nuo surfaces with more details.
PY - 2022
T2 - Scientific Programming
TI - Design of 3D Display System for Intangible Cultural Heritage Based on Generative Adversarial Network
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85135274699&doi=10.1155%2f2022%2f2944750&partnerID=40&md5=2844461d52d68f4b90892eae861d381a
VL - 2022
SN - 10589244 (ISSN)
ER -