mlsanityData to 7 Oct 2026

SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap

arXiv 2110.03101 ↗First posted 6 Oct 2021cs.CV cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Autonomous vision-based spaceborne navigation is an enabling technology for future on-orbit servicing and space logistics missions. While computer vision in general has benefited from Machine Learning (ML), training and validating spaceborne ML models are extremely challenging due to the impracticality of acquiring a large-scale labeled dataset of images of the intended target in the space environment. Existing datasets, such as Spacecraft PosE Estimation Dataset (SPEED), have so far mostly relied on synthetic images for both training and validation, which are easy to mass-produce but fail to resemble the visual features and illumination variability inherent to the target spaceborne images. In order to bridge the gap between the current practices and the intended applications in future space missions, this paper introduces SPEED+: the next generation spacecraft pose estimation dataset with specific emphasis on domain gap. In addition to 60,000 synthetic images for training, SPEED+ includes 9,531 hardware-in-the-loop images of a spacecraft mockup model captured from the Testbed for Rendezvous and Optical Navigation (TRON) facility. TRON is a first-of-a-kind robotic testbed capable of capturing an arbitrary number of target images with accurate and maximally diverse pose labels and high-fidelity spaceborne illumination conditions. SPEED+ is used in the second international Satellite Pose Estimation Challenge co-hosted by SLAB and the Advanced Concepts Team of the European Space Agency to evaluate and compare the robustness of spaceborne ML models trained on synthetic images.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 23 of its 52 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

23 of 52 references.

References · 23

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2017Decoupled Weight Decay Regularizationcited by 1,722
  6. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  10. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  11. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  12. 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
11 more
  1. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
  2. 2019Satellite Pose Estimation Challenge: Dataset, Competition Design and Resultscited by 62
  3. 2019Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinementcited by 56
  4. 2019Deep Learning for Spacecraft Pose Estimation from Photorealistic Renderingcited by 54
  5. 2019DeceptionNet: Network-Driven Domain Randomizationcited by 43
  6. 2018Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networkscited by 34
  7. 2018Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptationcited by 27
  8. 2019Towards Robust Learning-Based Pose Estimation of Noncooperative Spacecraftcited by 27
  9. 2021A Spacecraft Dataset for Detection, Segmentation and Parts Recognitioncited by 22
  10. 2021Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagerycited by 15
  11. 2021Robotic Testbed for Rendezvous and Optical Navigation: Multi-Source Calibration and Machine Learning Use Casescited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 7; 2024: 12; 2025: 16; 2026: 16.

57 papers.

Sort:

By area:

  1. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  2. 2022EarthNets: Empowering AI in Earth Observationcited by 40
  3. 2022Towards Bridging the Space Domain Gap for Satellite Pose Estimation using Event Sensingcited by 21
  4. 2022Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraintscited by 21
  5. 2023SPADES: A Realistic Spacecraft Pose Estimation Dataset using Event Sensingcited by 13
  6. 2022Spacecraft Pose Estimation Based on Unsupervised Domain Adaptation and on a 3D-Guided Loss Combinationcited by 12
  7. 20236D Object Pose Estimation from Approximate 3D Models for Orbital Roboticscited by 10
  8. 2024Characterizing Satellite Geometry via Accelerated 3D Gaussian Splattingcited by 8
  9. 2023Learning to Predict 3D Rotational Dynamics from Images of a Rigid Body with Unknown Mass Distributioncited by 7
  10. 2024Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operationscited by 7
  11. 2024Bridging the Domain Gap for Flight-Ready Spaceborne Visioncited by 6
  12. 2024Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesiscited by 5
38 more
  1. 2025Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimationcited by 5
  2. 2023On the Generation of a Synthetic Event-Based Vision Dataset for Navigation and Landingcited by 4
  3. 2025FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimationcited by 4
  4. 2022Lessons from a Space Lab -- An Image Acquisition Perspectivecited by 3
  5. 2024Event-based Structure-from-Orbitcited by 3
  6. 2024Domain Generalization for In-Orbit 6D Pose Estimationcited by 3
  7. 2024Test-Time Certifiable Self-Supervision to Bridge the Sim2Real Gap in Event-Based Satellite Pose Estimationcited by 3
  8. 2024How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?cited by 3
  9. 2023SU-Net: Pose estimation network for non-cooperative spacecraft on-orbitcited by 2
  10. 20233D-Aware Object Localization using Gaussian Implicit Occupancy Functioncited by 2
  11. 2025Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimationcited by 2
  12. 2025NeRF-based Visualization of 3D Cues Supporting Data-Driven Spacecraft Pose Estimationcited by 2
  13. 2025Improved 3D Gaussian Splatting of Unknown Spacecraft Structure Using Space Environment Illumination Knowledgecited by 2
  14. 2026SpaceSense-Bench: A Large-Scale Multi-Modal Benchmark for Spacecraft Perception and Pose Estimationcited by 2
  15. 2024Reconstructing Satellites in 3D from Amateur Telescope Imagescited by 1
  16. 2024Computer vision tasks for intelligent aerospace missions: An overviewcited by 1
  17. 2024Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesiscited by 1
  18. 2025Joint attitude estimation and 3D neural reconstruction of non-cooperative space objectscited by 1
  19. 2025Addressing Camera Sensors Faults in Vision-Based Navigation: Simulation and Dataset Developmentcited by 1
  20. 2025Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lightingcited by 1
  21. 2025A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Computerscited by 1
  22. 2025FPG-NAS: FLOPs-Aware Gated Differentiable Neural Architecture Search for Efficient 6DoF Pose Estimationcited by 1
  23. 2025On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraintscited by 1
  24. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  25. 2026Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Constructioncited by 1
  26. 2026Precision-Aware Illumination-Disentangled Vision Transformer for Spacecraft 6D Pose Estimationcited by 1
  27. 2023Modular Quantization-Aware Training for 6D Object Pose Estimationcited by 0
  28. 2024SpY: A Context-Based Approach to Spacecraft Component Detectioncited by 0
  29. 2025Deep Learning-Based Image Recovery and Pose Estimation for Resident Space Objectscited by 0
  30. 2025A large-scale, physically-based synthetic dataset for satellite pose estimationcited by 0
  31. 2025Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesiscited by 0
  32. 2025GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraftcited by 0
  33. 2025Domain Adaptive Object Detection for Space Applications with Real-Time Constraintscited by 0
  34. 2026Annotation Free Spacecraft Detection and Segmentation using Vision Language Modelscited by 0
  35. 2026SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicingcited by 0
  36. 2026Cross-Modal RGB-D Fusion Transformer for 6D Pose Estimation of Non-Cooperative Spacecraft with Stereo-Derived Depthcited by 0
  37. 2026NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertaintycited by 0
  38. 2026CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentationscited by 0

50 most cited of 57 All 57 (JSON)