mlsanityData to 7 Oct 2026

Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation

arXiv 2203.10339 ↗First posted 19 Mar 2022cs.CV cs.ROcited by 34

Not on the map. Why?

Abstract (arXiv)

6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular settings. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this limitation, we propose a novel monocular 6D pose estimation approach 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 current trends in noisy student training and differentiable rendering to further self-supervise the model on these unsupervised real RGB(-D) samples, seeking for a visually and geometrically optimal alignment. Moreover, employing both visible and amodal mask information, our self-supervision becomes very robust towards challenging scenarios such as occlusion. Extensive evaluations demonstrate that our proposed self-supervision outperforms all other methods relying on synthetic data or employing elaborate techniques from the domain adaptation realm. Noteworthy, our self-supervised approach consistently improves over its synthetically trained baseline and often almost closes the gap towards its fully supervised counterpart. The code and models are publicly available at https://github.com/THU-DA-6D-Pose-Group/self6dpp.git.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 78 of its 106 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

78 of 106 references.

References · 78

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  12. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
38 more
  1. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  2. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  4. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  5. 2020ResNeSt: Split-Attention Networkscited by 445
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  8. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  11. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  12. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  13. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  14. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  15. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  16. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  17. 2020State of the Art on Neural Renderingcited by 276
  18. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  19. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  20. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  21. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  22. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  23. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  24. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  25. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  26. 2019Disentangling Monocular 3D Object Detectioncited by 215
  27. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  28. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  29. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  30. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  31. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  32. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  33. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  34. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  35. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  36. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  37. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  38. 2020Differentiable Rendering: A Surveycited by 123

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 12; 2024: 11; 2025: 3; 2026: 4.

34 papers.

Sort:

By area:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 28
  3. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  4. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  5. 2022Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraintscited by 21
  6. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  7. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  8. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  9. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  10. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  11. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  12. 2024Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimationcited by 11
22 more
  1. 2023Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videoscited by 10
  2. 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimationcited by 10
  3. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  4. 2023A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Trainingcited by 6
  5. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 5
  6. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  7. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  8. 2024Test-Time Certifiable Self-Supervision to Bridge the Sim2Real Gap in Event-Based Satellite Pose Estimationcited by 3
  9. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  10. 2023Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Posecited by 2
  11. 2023S2P3: Self-Supervised Polarimetric Pose Predictioncited by 2
  12. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  13. 2024Good Grasps Only: A data engine for self-supervised fine-tuning of pose estimation using grasp poses for verificationcited by 2
  14. 2025Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Cameracited by 2
  15. 2024Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimationcited by 1
  16. 2024MaskVal: Simple but Effective Uncertainty Quantification for 6D Pose Estimationcited by 1
  17. 2024FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimationcited by 1
  18. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  19. 2023Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Datacited by 0
  20. 2026MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimationcited by 0
  21. 2026Semantic Prior Guided One-View 6D Pose Estimation for Novel Objectscited by 0
  22. 2026Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinementcited by 0