SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery

2026-06-26

AI Summary

This study addresses the degradation in 3D Gaussian Splatting (3DGS) reconstruction quality caused by illumination variations and insufficient geometric accuracy in multi-temporal, high-resolution satellite imagery with small convergence angles. To overcome these challenges, this work introduces 2D Gaussian Splatting (2DGS) into satellite photogrammetry for the first time. The proposed method integrates an affine camera model with online camera refinement based on sparse observations, while jointly incorporating geometric shadow mapping and per-camera color correction to effectively mitigate time-varying illumination and shadow artifacts. Evaluated on the DFC2019 and IARPA2016 datasets, the approach significantly outperforms existing 3DGS-based methods, achieving an 11.93% reduction in mean absolute error and a 31% decrease in peak GPU memory consumption.

Abstract

High-resolution satellite imagery demands 3D reconstruction methods that deliver both speed and geometric accuracy. Recent adaptations of 3D Gaussian Splatting (3DGS) to satellite imagery demonstrate strong efficiency, but reconstruction quality often degrades under diverse illumination across multi-date, high-altitude acquisitions (with small intersection angles), limiting applicability to remote sensing and vision tasks. We present SatSplat, the first framework to adapt 2D Gaussian Splatting (2DGS) to satellite photogrammetry, with online camera adjustment. We approximate satellite cameras with an affine model and learn a minimal delta parameterization for in-splat camera refinement from dense observations. The formulation is implemented with a 2DGS scene representation. To handle time-varying shadows and illumination changes, we integrate geometric shadow mapping and per-camera color correction during training. Across the evaluated DFC2019 and IARPA2016 benchmark sites, SatSplat achieves strong geometric accuracy while significantly outperforming prior 3DGS-based baselines. On our processed DFC2019 benchmark, SatSplat reduces mean absolute error by 11.93% and peak video memory by 31% relative to the previous state of the art. Our approach enables large-scale digital surface modeling with practical computational efficiency. The project page is available at https://gdaosu.github.io/satsplat/.

Problem

• satellite imagery
• 3D reconstruction
• geometric accuracy
• illumination variation
• multi-date acquisition

Innovation

• Gaussian Splatting
• satellite photogrammetry
• camera refinement
• illumination invariance
• digital surface modeling