SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wagner, Valentin, Bullinger, Sebastian, Arens, Michael, Stiefelhagen, Rainer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911538214862848
author Wagner, Valentin
Bullinger, Sebastian
Arens, Michael
Stiefelhagen, Rainer
author_facet Wagner, Valentin
Bullinger, Sebastian
Arens, Michael
Stiefelhagen, Rainer
contents 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 coarse-to-fine geometry-learning scheme, and Depth-Supervised Regularization stabilizes early training for improved geometric accuracy. On the DFC2019 satellite reconstruction benchmark, SatGeo-NeRF improves the Mean Altitude Error by 13.9% and 11.7% relative to state-of-the-art baselines such as EO-NeRF and EO-GS.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21931
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery
Wagner, Valentin
Bullinger, Sebastian
Arens, Michael
Stiefelhagen, Rainer
Computer Vision and Pattern Recognition
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 coarse-to-fine geometry-learning scheme, and Depth-Supervised Regularization stabilizes early training for improved geometric accuracy. On the DFC2019 satellite reconstruction benchmark, SatGeo-NeRF improves the Mean Altitude Error by 13.9% and 11.7% relative to state-of-the-art baselines such as EO-NeRF and EO-GS.
title SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.21931