KIT | KIT-Bibliothek | Impressum | Datenschutz

HoloGS: Instant Depth-based 3D Gaussian Splatting with Microsoft HoloLens 2

Jäger, Miriam 1; Kapler, Theodor; Feßenbecker, Michael; Birkelbach, Felix; Hillemann, Markus ORCID iD icon 1; Jutzi, Boris ORCID iD icon 1
1 Institut für Photogrammetrie und Fernerkundung (IPF), Karlsruher Institut für Technologie (KIT)

Abstract:

In the fields of photogrammetry, computer vision and computer graphics, the task of neural 3D scene reconstruction has led to the exploration of various techniques. Among these, 3D Gaussian Splatting stands out for its explicit representation of scenes using 3D Gaussians, making it appealing for tasks like 3D point cloud extraction and surface reconstruction. Motivated by its potential, we address the domain of 3D scene reconstruction, aiming to leverage the capabilities of the Microsoft HoloLens 2 for instant 3D Gaussian Splatting. We present HoloGS, a novel workflow utilizing HoloLens sensor data, which bypasses the need for pre-processing steps like Structure from Motion by instantly accessing the required input data i.e. the images, camera poses and the point cloud from depth sensing. We provide comprehensive investigations, including the training process and the rendering quality, assessed through the Peak Signal-to-Noise Ratio, and the geometric 3D accuracy of the densified point cloud from Gaussian centers, measured by Chamfer Distance. We evaluate our approach on two self-captured scenes: An outdoor scene of a cultural heritage statue and an indoor scene of a fine-structured plant. ... mehr


Volltext §
DOI: 10.5445/IR/1000172379
Veröffentlicht am 10.07.2024
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2024
Sprache Englisch
Identifikator KITopen-ID: 1000172379
Vorab online veröffentlicht am 03.05.2024
Schlagwörter 3D Gaussian Splatting, Microsoft HoloLens 2, Depth Sensor, Point Cloud, 3D Reconstruction, Neural Radiance Fields
Nachgewiesen in arXiv
Dimensions
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page