mlsanityData to 7 Oct 2026

Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras

arXiv 2203.08896 ↗First posted 16 Mar 2022cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

We introduce the Satellite Neural Radiance Field (Sat-NeRF), a new end-to-end model for learning multi-view satellite photogrammetry in the wild. Sat-NeRF combines some of the latest trends in neural rendering with native satellite camera models, represented by rational polynomial coefficient (RPC) functions. The proposed method renders new views and infers surface models of similar quality to those obtained with traditional state-of-the-art stereo pipelines. Multi-date images exhibit significant changes in appearance, mainly due to varying shadows and transient objects (cars, vegetation). Robustness to these challenges is achieved by a shadow-aware irradiance model and uncertainty weighting to deal with transient phenomena that cannot be explained by the position of the sun. We evaluate Sat-NeRF using WorldView-3 images from different locations and stress the advantages of applying a bundle adjustment to the satellite camera models prior to training. This boosts the network performance and can optionally be used to extract additional cues for depth supervision.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

27 of 54 references.

References · 27

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  6. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  7. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  8. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  10. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  11. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  12. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
15 more
  1. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  2. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  3. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  4. 2020State of the Art on Neural Renderingcited by 276
  5. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  6. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  7. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  8. 2018Semantic Stereo for Incidental Satellite Imagescited by 53
  9. 2021Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetrycited by 47
  10. 2019Leveraging Vision Reconstruction Pipelines for Satellite Imagerycited by 23
  11. 2021Rational Polynomial Camera Model Warping for Deep Learning Based Satellite Multi-View Stereo Matchingcited by 14
  12. 2019Late or Earlier Information Fusion from Depth and Spectral Data? Large-Scale Digital Surface Model Refinement by Hybrid-cGANcited by 7
  13. 2020ResDepth: Learned Residual Stereo Reconstructioncited by 7
  14. 2020A Generalized Multi-Task Learning Approach to Stereo DSM Filtering in Urban Areascited by 5
  15. 2021Robust Rational Polynomial Camera Modelling for SAR and Pushbroom Imagingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 15; 2025: 16; 2026: 16.

59 papers.

Sort:

By area:

  1. 2023Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictionscited by 38
  2. 2023SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Imagescited by 18
  3. 2025Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagerycited by 16
  4. 2024Gaussian Splatting for Efficient Satellite Image Photogrammetrycited by 15
  5. 2024SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite Imagerycited by 14
  6. 2025SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Imagescited by 13
  7. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  8. 2023Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Surveycited by 11
  9. 2023Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use casescited by 10
  10. 2025RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGScited by 10
  11. 2023SUNDIAL: 3D Satellite Understanding through Direct, Ambient, and Complex Lighting Decompositioncited by 9
  12. 2024Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Surveycited by 9
38 more
  1. 2023Incorporating Season and Solar Specificity into Renderings made by a NeRF Architecture using Satellite Imagescited by 8
  2. 2023Radar Fields: An Extension of Radiance Fields to SARcited by 7
  3. 2024Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagerycited by 6
  4. 2025Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervisioncited by 6
  5. 2024FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitionscited by 5
  6. 2025S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applicationscited by 5
  7. 2025From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Imagescited by 5
  8. 2022WorldGen: A Large Scale Generative Simulatorcited by 4
  9. 2024Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splattingcited by 4
  10. 2022Regularization of NeRFs using differential geometrycited by 3
  11. 2024Multiplane Prior Guided Few-Shot Aerial Scene Renderingcited by 3
  12. 2025Multi-view 3D surface reconstruction from SAR images by inverse renderingcited by 3
  13. 2025EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Renderingcited by 3
  14. 2026ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagerycited by 3
  15. 2026SatSurfGS: Generalizable 2D Gaussian Splatting for Sparse-View Satellite Surface Reconstructioncited by 3
  16. 2023Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Sizecited by 2
  17. 2023rpcPRF: Generalizable MPI Neural Radiance Field for Satellite Cameracited by 2
  18. 2024Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagerycited by 2
  19. 2024BRDF-NeRF: Neural Radiance Fields with Optical Satellite Images and BRDF Modellingcited by 2
  20. 2024Learning autonomous driving from aerial imagerycited by 2
  21. 2025Semantic Neural Radiance Fields for Multi-Date Satellite Datacited by 2
  22. 2025Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observationcited by 2
  23. 2026RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagerycited by 2
  24. 2026SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagerycited by 2
  25. 2024Depth Supervised Neural Surface Reconstruction from Airborne Imagerycited by 1
  26. 2024Exploring Seasonal Variability in the Context of Neural Radiance Fields for 3D Reconstruction on Satellite Imagerycited by 1
  27. 2024ARSGaussian: 3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesiscited by 1
  28. 2025TriDF: Triplane-Accelerated Density Fields for Few-Shot Remote Sensing Novel View Synthesiscited by 1
  29. 2026Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuningcited by 1
  30. 2023Improving NeRF with Height Data for Utilization of GIS Datacited by 0
  31. 2024psPRF:Pansharpening Planar Neural Radiance Field for Generalized 3D Reconstruction Satellite Imagerycited by 0
  32. 2024Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mappingcited by 0
  33. 2025SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagerycited by 0
  34. 2025Methods for evaluating the resolution of 3D data derived from satellite imagescited by 0
  35. 2025Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Renderingcited by 0
  36. 2025Delta-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfercited by 0
  37. 2026Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagerycited by 0
  38. 2026Sky2Ground: A Benchmark for Site Modeling under Varying Altitudecited by 0

50 most cited of 59 All 59 (JSON)