# SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite Imagery

arXiv: https://arxiv.org/abs/2403.18711 · HTML: https://mlsanity.com/paper/2403.18711/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [RobustNeRF: Ignoring Distractors with Robust Losses](https://mlsanity.com/paper/2302.00833/) (2023)
- [Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras](https://mlsanity.com/paper/2203.08896/) (2022)
- [Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry](https://mlsanity.com/paper/2104.09877/) (2021)
- [SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images](https://mlsanity.com/paper/2309.00277/) (2023)

## Built on by (most cited first, 14 of 14)

- [Gaussian Splatting for Efficient Satellite Image Photogrammetry](https://mlsanity.com/paper/2412.13047/) (2024)
- [Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision](https://mlsanity.com/paper/2502.08352/) (2025)
- [S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications](https://mlsanity.com/paper/2504.06920/) (2025)
- [ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery](https://mlsanity.com/paper/2601.00939/) (2026)
- [BRDF-NeRF: Neural Radiance Fields with Optical Satellite Images and BRDF Modelling](https://mlsanity.com/paper/2409.12014/) (2024)
- [Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation](https://mlsanity.com/paper/2507.01631/) (2025)
- [SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery](https://mlsanity.com/paper/2606.28581/) (2026)
- [Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning](https://mlsanity.com/paper/2605.07264/) (2026)
- [EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction](https://mlsanity.com/paper/2607.00417/) (2026)
- [Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction](https://mlsanity.com/paper/2603.18306/) (2026)
- [SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery](https://mlsanity.com/paper/2603.18634/) (2026)
- [SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting](https://mlsanity.com/paper/2606.27223/) (2026)
- [Robust 3D Reconstruction from Multi-View Optical Satellite Imagery via Reliability-Aware Height-Evidence Fusion in Gaussian Splatting](https://mlsanity.com/paper/2609.16772/) (2026)
- [Agentic Building-Aware Satellite Gaussian Splatting for Auditable Urban DSM Reconstruction](https://mlsanity.com/paper/2609.25578/) (2026)

## Abstract (arXiv)

Current stereo-vision pipelines produce high accuracy 3D reconstruction when using multiple pairs or triplets of satellite images. However, these pipelines are sensitive to the changes between images that can occur as a result of multi-date acquisitions. Such variations are mainly due to variable shadows, reflexions and transient objects (cars, vegetation). To take such changes into account, Neural Radiance Fields (NeRF) have recently been applied to multi-date satellite imagery. However, Neural methods are very compute-intensive, taking dozens of hours to learn, compared with minutes for standard stereo-vision pipelines. Following the ideas of Instant Neural Graphics Primitives we propose to use an efficient sampling strategy and multi-resolution hash encoding to accelerate the learning. Our model, Satellite Neural Graphics Primitives (SAT-NGP) decreases the learning time to 15 minutes while maintaining the quality of the 3D reconstruction.