mlsanityData to 7 Oct 2026

Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints

arXiv 2212.12103 ↗First posted 23 Dec 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models. To this end, we propose a self-training framework based on the domain-agnostic geometrical constraints. Specifically, we train a neural network to predict the 2D keypoints of a satellite and then use PnP to estimate the pose. The poses of target samples are regarded as latent variables to formulate the task as a minimization problem. Furthermore, we leverage fine-grained segmentation to tackle the information loss issue caused by abstracting the satellite as sparse keypoints. Finally, we iteratively solve the minimization problem in two steps: pseudo-label generation and network training. Experimental results show that our method adapts well to the target domain. Moreover, our method won the 1st place on the sunlamp task of the second international Satellite Pose Estimation Competition.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 36 of its 77 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

36 of 77 references.

References · 36

  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2017Decoupled Weight Decay Regularizationcited by 1,722
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  7. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  9. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  10. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  11. 2018Albumentations: fast and flexible image augmentationscited by 558
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
24 more
  1. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  2. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  3. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  4. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  5. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  6. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  7. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  8. 2020Unbiased Mean Teacher for Cross-domain Object Detectioncited by 158
  9. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  10. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  11. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  12. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  13. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  14. 2019Single-Stage 6D Object Pose Estimationcited by 88
  15. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
  16. 2019Satellite Pose Estimation Challenge: Dataset, Competition Design and Resultscited by 62
  17. 2021SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gapcited by 57
  18. 2019Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinementcited by 56
  19. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  20. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  21. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  22. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  23. 2019Towards Robust Learning-Based Pose Estimation of Noncooperative Spacecraftcited by 27
  24. 2020EfficientPose: Scalable single-person pose estimationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 6; 2026: 4.

21 papers.

Sort:

  1. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  2. 20236D Object Pose Estimation from Approximate 3D Models for Orbital Roboticscited by 10
  3. 2024Bridging the Domain Gap for Flight-Ready Spaceborne Visioncited by 6
  4. 2024Achieving Generalization in Orchestrating GNSS Interference Monitoring Stations Through Pseudo-Labelingcited by 6
  5. 2024Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesiscited by 5
  6. 2025Evaluation of (Un-)Supervised Machine Learning Methods for GNSS Interference Classification with Real-World Data Discrepanciescited by 5
  7. 2025FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimationcited by 4
  8. 2024Domain Generalization for In-Orbit 6D Pose Estimationcited by 3
  9. 2024Test-Time Certifiable Self-Supervision to Bridge the Sim2Real Gap in Event-Based Satellite Pose Estimationcited by 3
  10. 2024How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?cited by 3
  11. 2023SU-Net: Pose estimation network for non-cooperative spacecraft on-orbitcited by 2
  12. 2025ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopycited by 2
9 more
  1. 2023Neural-based Compression Scheme for Solar Image Datacited by 1
  2. 2024Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesiscited by 1
  3. 2025Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lightingcited by 1
  4. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  5. 2025Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesiscited by 0
  6. 2025Domain Adaptive Object Detection for Space Applications with Real-Time Constraintscited by 0
  7. 2026CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentationscited by 0
  8. 2026Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinementcited by 0
  9. 2026Robust PnP on a Neuromorphic Processor for Object Pose Estimationcited by 0