KIT | KIT-Bibliothek | Impressum | Datenschutz

Combining HoloLens with Instant-NeRFs: Advanced Real-Time 3D Mobile Mapping

Haitz, Dennis 1; Jutzi, Boris ORCID iD icon 1; Ulrich, Markus ORCID iD icon 1; Jäger, Miriam 1; Huebner, Patrick 1
1 Institut für Photogrammetrie und Fernerkundung (IPF), Karlsruher Institut für Technologie (KIT)

Abstract:

This work represents a large step into modern ways of fast 3D reconstruction based on RGB camera images. Utilizing a Microsoft HoloLens 2 as a multisensor platform that includes an RGB camera and an inertial measurement unit for SLAM-based camera-pose determination, we train a Neural Radiance Field (NeRF) as a neural scene representation in real-time with the acquired data from the HoloLens. The HoloLens is connected via Wifi to a high-performance PC that is responsible for the training and 3D reconstruction. After the data stream ends, the training is stopped and the 3D reconstruction is initiated, which extracts a point cloud of the scene. With our specialized inference algorithm, five million scene points can be extracted within 1 second. In addition, the point cloud also includes radiometry per point. Our method of 3D reconstruction outperforms grid point sampling with NeRFs by multiple orders of magnitude and can be regarded as a complete real-time 3D reconstruction method in a mobile mapping setup.


Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2023
Sprache Englisch
Identifikator KITopen-ID: 1000159529
Verlag arxiv
Umfang 8 S.
Vorab online veröffentlicht am 03.05.2023
Schlagwörter Computer Vision and Pattern Recognition (cs.CV)
Nachgewiesen in Dimensions
arXiv
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page