# Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry

arXiv: https://arxiv.org/abs/2104.09877 · HTML: https://mlsanity.com/paper/2104.09877/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images](https://mlsanity.com/paper/2007.09892/) (2020)
- [IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network](https://mlsanity.com/paper/1802.10249/) (2018)
- [Learning Implicit Surface Light Fields](https://mlsanity.com/paper/2003.12406/) (2020)
- [Multi-Task Learning of Height and Semantics from Aerial Images](https://mlsanity.com/paper/1911.07543/) (2019)
- [End-to-End Training of Hybrid CNN-CRF Models for Stereo](https://mlsanity.com/paper/1611.10229/) (2016)
- [GeLaTO: Generative Latent Textured Objects](https://mlsanity.com/paper/2008.04852/) (2020)

## Built on by (most cited first, 30 of 47)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)](https://mlsanity.com/paper/2210.00379/) (2022)
- [D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video](https://mlsanity.com/paper/2205.15838/) (2022)
- [Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras](https://mlsanity.com/paper/2203.08896/) (2022)
- [Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions](https://mlsanity.com/paper/2306.17624/) (2023)
- [WaterNeRF: Neural Radiance Fields for Underwater Scenes](https://mlsanity.com/paper/2209.13091/) (2022)
- [SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images](https://mlsanity.com/paper/2309.00277/) (2023)
- [Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery](https://mlsanity.com/paper/2510.15869/) (2025)
- [Gaussian Splatting for Efficient Satellite Image Photogrammetry](https://mlsanity.com/paper/2412.13047/) (2024)
- [Gaussian Shadow Casting for Neural Characters](https://mlsanity.com/paper/2401.06116/) (2024)
- [SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite Imagery](https://mlsanity.com/paper/2403.18711/) (2024)
- [SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images](https://mlsanity.com/paper/2508.09479/) (2025)
- [Neural Radiance Fields for the Real World: A Survey](https://mlsanity.com/paper/2501.13104/) (2025)
- [ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields](https://mlsanity.com/paper/2201.09968/) (2022)
- [SUNDIAL: 3D Satellite Understanding through Direct, Ambient, and Complex Lighting Decomposition](https://mlsanity.com/paper/2312.16215/) (2023)
- [Incorporating Season and Solar Specificity into Renderings made by a NeRF Architecture using Satellite Images](https://mlsanity.com/paper/2308.01262/) (2023)
- [Radar Fields: An Extension of Radiance Fields to SAR](https://mlsanity.com/paper/2312.12961/) (2023)
- [Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery](https://mlsanity.com/paper/2405.11021/) (2024)
- [Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision](https://mlsanity.com/paper/2502.08352/) (2025)
- [FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions](https://mlsanity.com/paper/2409.15132/) (2024)
- [S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications](https://mlsanity.com/paper/2504.06920/) (2025)
- [From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images](https://mlsanity.com/paper/2512.07527/) (2025)
- [Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting](https://mlsanity.com/paper/2501.00625/) (2024)
- [ImplicitTerrain: a Continuous Surface Model for Terrain Data Analysis](https://mlsanity.com/paper/2406.00227/) (2024)
- [Multiplane Prior Guided Few-Shot Aerial Scene Rendering](https://mlsanity.com/paper/2406.04961/) (2024)
- [EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering](https://mlsanity.com/paper/2511.16542/) (2025)
- [ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery](https://mlsanity.com/paper/2601.00939/) (2026)
- [Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Size](https://mlsanity.com/paper/2309.11767/) (2023)
- [rpcPRF: Generalizable MPI Neural Radiance Field for Satellite Camera](https://mlsanity.com/paper/2310.07179/) (2023)
- [BRDF-NeRF: Neural Radiance Fields with Optical Satellite Images and BRDF Modelling](https://mlsanity.com/paper/2409.12014/) (2024)

## Abstract (arXiv)

We present a new generic method for shadow-aware multi-view satellite photogrammetry of Earth Observation scenes. Our proposed method, the Shadow Neural Radiance Field (S-NeRF) follows recent advances in implicit volumetric representation learning. For each scene, we train S-NeRF using very high spatial resolution optical images taken from known viewing angles. The learning requires no labels or shape priors: it is self-supervised by an image reconstruction loss. To accommodate for changing light source conditions both from a directional light source (the Sun) and a diffuse light source (the sky), we extend the NeRF approach in two ways. First, direct illumination from the Sun is modeled via a local light source visibility field. Second, indirect illumination from a diffuse light source is learned as a non-local color field as a function of the position of the Sun. Quantitatively, the combination of these factors reduces the altitude and color errors in shaded areas, compared to NeRF. The S-NeRF methodology not only performs novel view synthesis and full 3D shape estimation, it also enables shadow detection, albedo synthesis, and transient object filtering, without any explicit shape supervision.