mlsanityData to 7 Oct 2026

Multi-path Learning for Object Pose Estimation Across Domains

arXiv 1908.00151 ↗First posted 1 Aug 2019cs.CV stat.MLcited by 52

Not on the map. Why?

Abstract (arXiv)

We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during training, but can also relate views of untrained objects. Our single-encoder-multi-decoder network is trained using a technique we denote "multi-path learning": While the encoder is shared by all objects, each decoder only reconstructs views of a single object. Consequently, views of different instances do not have to be separated in the latent space and can share common features. The resulting encoder generalizes well from synthetic to real data and across various instances, categories, model types and datasets. We systematically investigate the learned encodings, their generalization, and iterative refinement strategies on the ModelNet40 and T-LESS dataset. Despite training jointly on multiple objects, our 6D Object Detection pipeline achieves state-of-the-art results on T-LESS at much lower runtimes than competing approaches.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 18; 2023: 12; 2024: 9; 2025: 3; 2026: 1.

52 papers.

Sort:

By area:

  1. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  2. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  3. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  4. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  5. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  6. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  7. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  8. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  9. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  10. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  11. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  12. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
38 more
  1. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  2. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  3. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  4. 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
  5. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  6. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  7. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  8. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  9. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  10. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
  11. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  12. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  13. 2021ZePHyR: Zero-shot Pose Hypothesis Ratingcited by 26
  14. 2022Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraintscited by 21
  15. 2022Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Pickingcited by 20
  16. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  17. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  18. 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
  19. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  20. 2021Polarimetric Pose Predictioncited by 16
  21. 2022PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Trackingcited by 15
  22. 2021DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimationcited by 12
  23. 2022Unseen Object 6D Pose Estimation: A Benchmark and Baselinescited by 12
  24. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  25. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  26. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  27. 2023Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objectscited by 9
  28. 2022OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimationcited by 8
  29. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  30. 2021Occlusion-Robust Object Pose Estimation with Holistic Representationcited by 6
  31. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  32. 2021Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervisioncited by 3
  33. 2025ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Pickingcited by 2
  34. 2022Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representationcited by 1
  35. 2023MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimationcited by 1
  36. 2024CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimationcited by 1
  37. 2023Jenga Stacking Based on 6D Pose Estimation for Architectural Form Finding Processcited by 0
  38. 2024Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimationcited by 0

50 most cited of 52 All 52 (JSON)