mlsanityData to 7 Oct 2026

Vision-based Neural Scene Representations for Spacecraft

arXiv 2105.06405 ↗First posted 11 May 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In advanced mission concepts with high levels of autonomy, spacecraft need to internally model the pose and shape of nearby orbiting objects. Recent works in neural scene representations show promising results for inferring generic three-dimensional scenes from optical images. Neural Radiance Fields (NeRF) have shown success in rendering highly specular surfaces using a large number of images and their pose. More recently, Generative Radiance Fields (GRAF) achieved full volumetric reconstruction of a scene from unposed images only, thanks to the use of an adversarial framework to train a NeRF. In this paper, we compare and evaluate the potential of NeRF and GRAF to render novel views and extract the 3D shape of two different spacecraft, the Soil Moisture and Ocean Salinity satellite of ESA's Living Planet Programme and a generic cube sat. Considering the best performances of both models, we observe that NeRF has the ability to render more accurate images regarding the material specularity of the spacecraft and its pose. For its part, GRAF generates precise novel views with accurate details even when parts of the satellites are shadowed while having the significant advantage of not needing any information about the relative pose.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

30 of 54 references.

References · 30

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  10. 2018Demystifying MMD GANscited by 1,268
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  12. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
18 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  2. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  3. 2017Neural 3D Mesh Renderercited by 437
  4. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  5. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  6. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  7. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  8. 2020State of the Art on Neural Renderingcited by 276
  9. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  10. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  11. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  12. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  13. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  14. 2017Generative Face Completioncited by 79
  15. 2019Satellite Pose Estimation Challenge: Dataset, Competition Design and Resultscited by 62
  16. 2021Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagerycited by 15
  17. 2020AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representationcited by 14
  18. 2020L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasetscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 1; 2024: 3; 2025: 5; 2026: 2.

12 papers.

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 20233D Reconstruction of Non-cooperative Resident Space Objects using Instant NGP-accelerated NeRF and D-NeRFcited by 9
  3. 2024Characterizing Satellite Geometry via Accelerated 3D Gaussian Splattingcited by 8
  4. 2024Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operationscited by 7
  5. 2025Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observationcited by 2
  6. 2025Improved 3D Gaussian Splatting of Unknown Spacecraft Structure Using Space Environment Illumination Knowledgecited by 2
  7. 2024Computer vision tasks for intelligent aerospace missions: An overviewcited by 1
  8. 2025Joint attitude estimation and 3D neural reconstruction of non-cooperative space objectscited by 1
  9. 2025Dynamic Scene 3D Reconstruction of an Uncooperative Resident Space Objectcited by 1
  10. 2025On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraintscited by 1
  11. 2026From Images2Mesh: A 3D Surface Reconstruction Pipeline for Non-Cooperative Space Objectscited by 0
  12. 2026NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertaintycited by 0