mlsanityData to 7 Oct 2026

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

arXiv 2004.06468 ↗First posted 14 Apr 2020cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even from monocular images. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this shortcoming, we propose the idea of monocular 6D pose estimation by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB data, we leverage recent advances in neural rendering to further self-supervise the model on unannotated real RGB-D data, seeking for a visually and geometrically optimal alignment. Extensive evaluations demonstrate that our proposed self-supervision is able to significantly enhance the model's original performance, outperforming all other methods relying on synthetic data or employing elaborate techniques from the domain adaptation realm.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 24; 2023: 18; 2024: 15; 2025: 5; 2026: 2.

79 papers.

Sort:

  1. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  2. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  3. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  4. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  5. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  6. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  7. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  8. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  9. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  10. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  11. 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
  12. 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
38 more
  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  3. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  4. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  5. 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
  6. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  7. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  8. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  9. 2021DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstrationcited by 20
  10. 2022Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Pickingcited by 20
  11. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19
  12. 2023FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objectscited by 18
  13. 2021StablePose: Learning 6D Object Poses from Geometrically Stable Patchescited by 17
  14. 2021T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regressioncited by 16
  15. 2024High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimizationcited by 15
  16. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  17. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  18. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  19. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  20. 2022Towards Self-Supervised Category-Level Object Pose and Size Estimationcited by 11
  21. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  22. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  23. 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimationcited by 9
  24. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
  25. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  26. 2024CRISP: Object Pose and Shape Estimation with Test-Time Adaptationcited by 9
  27. 2022Sim2Real Object-Centric Keypoint Detection and Descriptioncited by 8
  28. 2024OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimationcited by 8
  29. 2022Semantic keypoint-based pose estimation from single RGB framescited by 7
  30. 2023A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Trainingcited by 6
  31. 2023Tracking by 3D Model Estimation of Unknown Objects in Videoscited by 5
  32. 2023DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimationcited by 5
  33. 2022Uni6Dv2: Noise Elimination for 6D Pose Estimationcited by 4
  34. 2023Differentiable Shadow Mapping for Efficient Inverse Graphicscited by 4
  35. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  36. 2024NeRF-Feat: 6D Object Pose Estimation using Feature Renderingcited by 4
  37. 2025MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learningcited by 4
  38. 20256D Strawberry Pose Estimation: Real-time and Edge AI Solutions Using Purely Synthetic Training Datacited by 4

50 most cited of 79 All 79 (JSON)