# SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery

arXiv: https://arxiv.org/abs/2603.21931 · HTML: https://mlsanity.com/paper/2603.21931/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](https://mlsanity.com/paper/2303.07418/) (2023)
- [Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry](https://mlsanity.com/paper/2104.09877/) (2021)
- [Leveraging Vision Reconstruction Pipelines for Satellite Imagery](https://mlsanity.com/paper/1910.02989/) (2019)
- [SUNDIAL: 3D Satellite Understanding through Direct, Ambient, and Complex Lighting Decomposition](https://mlsanity.com/paper/2312.16215/) (2023)
- [Surface Normal Clustering for Implicit Representation of Manhattan Scenes](https://mlsanity.com/paper/2212.01331/) (2022)
- [Semantic Neural Radiance Fields for Multi-Date Satellite Data](https://mlsanity.com/paper/2502.16992/) (2025)

## Abstract (arXiv)

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.