EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparative Assessment of Neural Radiance Fields and 3D Gaussian Splatting for Point Cloud Generation from UAV Imagery

Muhammed Enes Atik iD

Sensors · 09.05.2025 · 25 (10) · 2995

DOI: 10.3390/s25102995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.05.2025. Verfasst von Muhammed Enes Atik. Beteiligte Einrichtung: Department of Geomatics Engineering, Faculty of Civil Engineering, Istanbul Technical University, Istanbul 34469, Türkiye. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point clouds continue to be the main data source in 3D modeling studies with unmanned aerial vehicle (UAV) images. Structure-from-Motion (SfM) and MultiView Stereo (MVS) have high time costs for point cloud generation, especially in large data sets. For this reason, state-of-the-art methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful alternatives for point cloud generation. This paper explores the performance of NeRF and 3DGS methods in generating point clouds from UAV images. For this purpose, the Nerfacto, Instant-NGP, and Splatfacto methods developed in the Nerfstudio framework were used. The obtained point clouds were evaluated by taking the point cloud produced with the photogrammetric method as reference. In this study, the effects of image size and iteration number on the performance of the algorithms were investigated in two different study areas. According to the results, Splatfacto demonstrates promising capabilities in addressing challenges related to scene complexity, rendering efficiency, and accuracy in UAV imagery.

Schlagwörter

Stichwörter der Autor:innen

NeRFUAVartificial intelligencegaussian splattingmultiview stereophotogrammetrypoint cloudstructure from motion

Autor:innen und Institutionen

  • Department of Geomatics Engineering, Faculty of Civil Engineering, Istanbul Technical University, Istanbul 34469, Türkiye.

ORCID-Profile: Muhammed Enes Atik

Zitieren

APA

Atik, M. E. (2025). Comparative Assessment of Neural Radiance Fields and 3D Gaussian Splatting for Point Cloud Generation from UAV Imagery. Sensors, 25(10), 2995. https://doi.org/10.3390/s25102995

Vancouver

Atik ME. Comparative Assessment of Neural Radiance Fields and 3D Gaussian Splatting for Point Cloud Generation from UAV Imagery. Sensors. 2025;25(10):2995. doi:10.3390/s25102995

BibTeX
@article{Atik2025,
  author = {Atik, Muhammed Enes},
  title = {Comparative Assessment of Neural Radiance Fields and 3D Gaussian Splatting for Point Cloud Generation from UAV Imagery},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {10},
  pages = {2995},
  doi = {10.3390/s25102995}
}
Kostenlos starten →