Generative AI Tool Pipeline for Creating Artificial Historical Characters for Cultural Heritage XR

Abstract

In our project, we aimed to create historically authentic and vivid virtual representations of historic personalities that are connected to the regional Fichtelgebirge (Bavaria, Germany) to support the storytelling of our immersive XR applications. We are describing the tools in detail, the process of the tool chain and the resulting media. Next, we are discussing the challenges in media production like historical correctness and the consultation of historians. In order to create visual reproducibility we are explaining the detailed text prompts, their limitations and how to cope with resulting errors of the human physiognomy. Finally, we are briefly describing the application of the animated and talking generated historic characters in an immersive interactive WebXR environment. The XR experience is presented in web browsers on smartphones, tablets and XR headsets and the underlying software is based on the open-source framework Aframe. Our paper will describe the process, the results and the limitations in detail. Furthermore, we will provide a flow chart of the tool pipeline with visual examples of these aspects. The animations and voices of the historic characters will be demonstrated in videos of the XR application.

mehr

Mehr zum Titel

Titel	Generative AI Tool Pipeline for Creating Artificial Historical Characters for Cultural Heritage XR
Medien	International Conference on Human-Computer Interaction
Verlag	Springer Nature Switzerland
Heft	---
Band	2024
ISBN	---
Verfasser/Herausgeber	Prof. Michael Zöllner, Jan Gemeinhardt
Seiten	41-46
Veröffentlichungsdatum	06.07.2024
Projekttitel	---
Zitation	Zöllner, Michael; Gemeinhardt, Jan (2024): Generative AI Tool Pipeline for Creating Artificial Historical Characters for Cultural Heritage XR. International Conference on Human-Computer Interaction 2024, S. 41-46. DOI: 10.1007/978-3-031-61950-2_5