Orthophoto generation from sparse views via structurally consistent prior-guided 3D Gaussian splatting
Journal of Applied Remote Sensing · 17.11.2025 · 19 (04) · 1-23
DOI: 10.1117/1.jrs.19.044506 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Remote Sensing, erschienen am 17.11.2025. Verfasst von Zhenglong Cai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref). Gefördert von: “Research on 3D Gaussian Splatting Reconstruction and Visualization Techniques for Air-Ground Collaborative Systems”, National Natural Science Foundation of China.
Abstract (Originalsprache)
To address geometric distortion, texture artifacts, and low reconstruction efficiency in orthophoto generation from sparse views, we propose a structure-consistent 3D Gaussian splatting method. By incorporating matching priors, the method enforces 3D structural consistency, reducing surface discontinuities and voids. A differentiable orthographic projection is designed to generate orthophotos from sparse inputs. Experiments over a 10 km2 area using only 36 images (191 m altitude, 4 m focal length) show that our approach substantially improves geometric completeness and texture fidelity compared with traditional methods and unmodified 3DGS. The method achieves efficiency gains of 31.5% over 3DGS and 6.9% to 9.1% over commercial software (ContextCapture, MetaShape, Pix4D). Under sparse-view conditions, it attains an average absolute error of ∼0.22 m and an average relative error of 0.52%, comparable to traditional software, demonstrating reliable geometric precision and robustness for high-quality orthophoto generation with limited image coverage.
Förderung
- “Research on 3D Gaussian Splatting Reconstruction and Visualization Techniques for Air-Ground Collaborative Systems”
- National Natural Science Foundation of China
Zitieren
APA
Cai, Z., Huang, H., Ye, T., Bian, W., Wang, T., & Yang, J. (2025). Orthophoto generation from sparse views via structurally consistent prior-guided 3D Gaussian splatting. Journal of Applied Remote Sensing, 19(04), 1-23. https://doi.org/10.1117/1.jrs.19.044506
Vancouver
Cai Z, Huang H, Ye T, Bian W, Wang T, Yang J. Orthophoto generation from sparse views via structurally consistent prior-guided 3D Gaussian splatting. Journal of Applied Remote Sensing. 2025;19(04):1-23. doi:10.1117/1.jrs.19.044506
BibTeX
@article{Cai2025,
author = {Cai, Zhenglong and Huang, He and Ye, Tong and Bian, Wenyao and Wang, Tianjiao and Yang, Junxing},
title = {Orthophoto generation from sparse views via structurally consistent prior-guided 3D Gaussian splatting},
journal = {Journal of Applied Remote Sensing},
year = {2025},
volume = {19},
number = {04},
pages = {1--23},
doi = {10.1117/1.jrs.19.044506}
}
EUVIMED