ISPRS-Annals

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

ISPRS-Annals

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

2194-9050

Copernicus Publications

Göttingen, Germany

10.5194/isprs-annals-XI-2-2026-367-2026

SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery

Wagner

Valentin

¹ Bullinger

Sebastian

¹ Arens

Michael

¹ Stiefelhagen

Rainer

Object Recognition, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB , Ettlingen, Germany

Computer Vision for Human-Computer Interaction Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany

03 07 2026

XI-2-2026 367 374

2026

This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

This article is available from https://isprs-annals.copernicus.org/articles/XI-2-2026/367/2026/isprs-annals-XI-2-2026-367-2026.html

The full text article is available as a PDF file from https://isprs-annals.copernicus.org/articles/XI-2-2026/367/2026/isprs-annals-XI-2-2026-367-2026.pdf

We present SatGeo-NeRF, a geometrically regularized NeRF for satellite imagery that mitigates overfitting-induced geometric artifacts observed in current state-of-the-art models using three model-agnostic regularizers. Gravity-Aligned Planarity Regularization aligns depth-inferred, approximated surface normals with the gravity axis to promote local planarity, coupling adjacent rays via a corresponding surface approximation to facilitate cross-ray gradient flow. Granularity Regularization enforces a progressive coarse-to-fine geometry-learning scheme, and Depth-Supervised Regularization stabilizes early training using sparse depth cues for improved geometric accuracy. On the DFC2019 satellite reconstruction benchmark, SatGeo-NeRF improves the Mean Altitude Error by 14.0% and 11.4% relative to state-of-the-art baselines such as EO-NeRF and EO-GS.