Optimised models for AR/VR by using geometric complexity metrics to control tessellation
Year: 2023
Editor: Kevin Otto, Boris Eisenbart, Claudia Eckert, Benoit Eynard, Dieter Krause, Josef Oehmen, Nad
Author: Dammann, Maximilian Peter; Steger, Wolfgang; Paetzold-Byhain, Kristin
Series: ICED
Institution: Technische Universit
Section: Design Methods
Page(s): 2855-2864
DOI number: https://doi.org/10.1017/pds.2023.286
ISBN: -
ISSN: -
Abstract
AR/VR applications are a valuable tool in product design and lifecycle. But the integration of AR/VR is not seamless, as CAD models need to be prepared for the AR/VR applications. One necessary data transformation is the tessellation of the analytically described geometry. To ensure the usability, visual quality and evaluability of the AR/VR application, time consuming optimisation is needed depending on the product complexity and the performance of the target device.
Widespread approaches to this problem are based on iterative mesh decimation. This approach ignores the varying importance of geometries and the required visual quality in engineering applications. Our predictive approach is an alternative that enables optimisation without iterative process steps on the tessellated geometry.
The contribution presents an approach that uses surface-based prediction and enables predictions of the perceived visual quality of the geometries. This contains the investigation of different geometric complexity metrics gathered from literature as basis for prediction models. The approach is implemented in a geometry preparation tool and the results are compared with other approaches.
Keywords: Virtual reality, Visualisation, Machine learning, Optimisation