3D Reconstruction and Transparent Visualization of Indonesian Cultural Heritage from a Single Image

Simple item page
dc.contributor.authorPan, Jiaoen_US
dc.contributor.authorLi, Liangen_US
dc.contributor.authorYamaguchi, Hiroshien_US
dc.contributor.authorHasegawa, Kyokoen_US
dc.contributor.authorThufail, Fadjar I.en_US
dc.contributor.authorMantara, Braen_US
dc.contributor.authorTanaka, Satoshien_US
dc.contributor.editorSablatnig, Robert and Wimmer, Michaelen_US
dc.date.accessioned2018-11-11T10:57:41Z
dc.date.available2018-11-11T10:57:41Z
dc.date.issued2018
dc.description.abstractHerein, we propose a method for three-dimensional (3D) reconstruction of cultural heritage based on deep learning, which we apply to the reliefs of the Buddhist temple heritage of Borobudur Temple, in Indonesia. Some parts of the Borobudur reliefs have been hidden by stone walls and are not visible following the reinforcements during the Dutch rule. Today, only gray-scale photos of those hidden parts are displayed in the Borobudur Museum. First, we reconstruct 3D point clouds of the hidden reliefs from these photos and predict the pixel-wise depth information for each of them using a deep neural network model. We then apply our stochastic point-based rendering mechanism to produce a high-quality visualization of the reconstructed point clouds. We have achieved promising visualization results that provide us with an intuitive understanding of the valuable relief heritage that is no longer visible to ordinary visitors.en_US
dc.description.sectionheaders3D Scanning and Digitization
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage
dc.identifier.doi10.2312/gch.20181363
dc.identifier.isbn978-3-03868-057-4
dc.identifier.issn2312-6124
dc.identifier.pages207-210
dc.identifier.urihttps://doi.org/10.2312/gch.20181363
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/gch20181363
dc.publisherThe Eurographics Associationen_US
dc.subjectApplied computing
dc.subjectDigital libraries and archives
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectHuman
dc.subjectcentered computing
dc.subjectVisualization
dc.title3D Reconstruction and Transparent Visualization of Indonesian Cultural Heritage from a Single Imageen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
207-210.pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
reconsructedpt.mp4
Size:
25.17 MB
Format:
Unknown data format
Download
Collections
GCH 2018 - Eurographics Workshop on Graphics and Cultural Heritage