mlsanityData to 7 Oct 2026

Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation

arXiv 2311.09500 ↗First posted 16 Nov 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We address the simulation-to-real domain gap in six degree-of-freedom pose estimation (6DoF PE), and propose a novel self-supervised keypoint voting-based 6DoF PE framework, effectively narrowing this gap using a learnable kernel in RKHS. We formulate this domain gap as a distance in high-dimensional feature space, distinct from previous iterative matching methods. We propose an adapter network, which is pre-trained on purely synthetic data with synthetic ground truth poses, and which evolves the network parameters from this source synthetic domain to the target real domain. Importantly, the real data training only uses pseudo-poses estimated by pseudo-keypoints, and thereby requires no real ground truth data annotations. Our proposed method is called RKHSPose, and achieves state-of-the-art performance among self-supervised methods on three commonly used 6DoF PE datasets including LINEMOD (+4.2%), Occlusion LINEMOD (+2%), and YCB-Video (+3%). It also compares favorably to fully supervised methods on all six applicable BOP core datasets, achieving within -11.3% to +0.2% of the top fully supervised results.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 61 of its 96 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

61 of 96 references.

References · 61

  1. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  2. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  5. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  6. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  7. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  8. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  9. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  10. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  11. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  12. 2020When Do Neural Networks Outperform Kernel Methods?cited by 150
38 more
  1. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  2. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  3. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  4. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 129
  5. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  6. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  7. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  8. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 100
  9. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  10. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  11. 2019HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptationcited by 89
  12. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  13. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  14. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  15. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  16. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  17. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  18. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  19. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  20. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  21. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  22. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  23. 2014Convolutional Kernel Networkscited by 47
  24. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  25. 2020Convolutional Kernel Networks for Graph-Structured Datacited by 38
  26. 2021Reproducing Kernel Hilbert Space, Mercer's Theorem, Eigenfunctions, Nystr"om Method, and Use of Kernels in Machine Learning: Tutorial and Surveycited by 36
  27. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  28. 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
  29. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  30. 2022DPODv2: Dense Correspondence-Based 6 DoF Pose Estimationcited by 32
  31. 2016End-to-End Kernel Learning with Supervised Convolutional Kernel Networkscited by 28
  32. 2019Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Pickingcited by 25
  33. 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
  34. 2021Conditional Bures Metric for Domain Adaptationcited by 25
  35. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  36. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  37. 2021Learning with convolution and pooling operations in kernel methodscited by 21
  38. 2020Single Shot 6D Object Pose Estimationcited by 19

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Self-Supervised Learning Using Nonlinear Dependencecited by 3
  2. 2025Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Cameracited by 2
  3. 2025Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Spacecited by 2
  4. 2026Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Featurescited by 0