- Titel
- Processing History
- Untertitel
- Potentials of Transformers for 3D Reconstruction of Historical Objects with the Help of Artifcial Intelligence
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-784132
- Konferenz
- Gemeinschaften in Neuen Medien. Dresden, 07.-08.10.2021
- Quellenangabe
- Gemeinschaften in Neuen Medien. Digitale Partizipation in hybriden Realitäten und Gemeinschaften. : 24. Workshop GeNeMe'21 Gemeinschaften in Neuen Medien
Herausgeber: Prof. Dr. Thomas Köhler, Prof. Dr. Eric Schoop, Prof. Dr. Nina Kahnwald, Prof. Dr. Ralph Sonntag
Erscheinungsort: Dresden
Verlag: TUDpress
Erscheinungsjahr: 2021
Seiten: 191-201
ISBN: 978-3-95908-235-8 - Erstveröffentlichung
- 2021
- DOI
- https://doi.org/10.25368/2022.41
- Abstract (EN)
- The digital preservation of cultural heritage is an important and challenging task for the research community. Reconstructing historical objects, which do not exist anymore, in the form of digital 3D models makes it possible to visualize them and present them to the public. The reconstruction process as well as the visualization lead to a deeper understanding of the lost historical objects. But the process of the digitalreconstruction is complex and time consuming as diverse sources have to be consulted and interpreted. Therefore, in this paper the latest technology in the feld of artifcial intelligence (AI) is used to support researchers in the feld of Digital Humanities: A Transformer deep learning model based on questions answering methods is introduced to assist to digitally reconstruct historical objects in 3D. It implies a new dimension of data availability, which supports the knowledge process by making large amounts of data qualitatively accessible. [Aus: Einleitung]
- Freie Schlagwörter (DE)
- GeNeMe 2021, Wissensmanagement, Transformation, Wissensgemeinschaften, Rekonstruktion historischer Objekte
- Freie Schlagwörter (EN)
- GeNeMe 2021, knowledge management, transformation, knowledge communities, preservation of cultural heritage, Reconstructing historical objects
- Klassifikation (DDC)
- 330
- Klassifikation (RVK)
- QR 760
- Verlag
- TUDpress, Dresden
- Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-784132
- Veröffentlichungsdatum Qucosa
- 11.03.2022
- Dokumenttyp
- Konferenzbeitrag
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY-SA 4.0