Nerf(acto) for 3D modeling of the DRZ outside testing area
- The video shows a very high resolution 3D point cloud !!! of the outdoor area of the German Rescue Robotics Center. For the recording, a 25-second POI flight was performed with a Mavic 3. From the 4K video footage captured during this flight, 77 images were cropped and localized within 4 minutes using colmap and processed using Neural Radiance Fields (NeRF). The nerfacto model of Nerfstudio was trained on an Nvidia RTX 4090 for 8 minutes. In summary, a top 3D model is available to task forces after about 13 minutes. The calculation is performed locally on site by the RobLW of the DRZ. The video shown here shows a free camera path rendered at 60 hz (Full HD).
Author: | Julien Meine, Niklas Voigt, Jan-Niklas Kremer, Niklas Digakis, Max Schulte, Hartmut Surmann |
---|---|
URN: | urn:nbn:de:hbz:1010-opus4-43156 |
Document Type: | video |
Language: | English |
Date of Publication (online): | 2023/06/26 |
Date of first Publication: | 2023/06/26 |
Publishing Institution: | Westfälische Hochschule Gelsenkirchen Bocholt Recklinghausen |
Release Date: | 2024/01/26 |
Departments / faculties: | Fachbereiche / Informatik und Kommunikation |
Dewey Decimal Classification: | Informatik, Informationswissenschaft, allgemeine Werke / Informatik, Wissen, Systeme / Datenverarbeitung; Informatik |
Licence (German): | Creative Commons - Namensnennung |