SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery
This work addresses overfitting issues in satellite image reconstruction for remote sensing applications, representing an incremental improvement over existing methods.
The paper tackles geometric artifacts in NeRF models for satellite imagery by introducing three model-agnostic regularizers, resulting in a 13.9% and 11.7% improvement in Mean Altitude Error on the DFC2019 benchmark compared to state-of-the-art baselines.
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.