mlsanityData to 7 Oct 2026

Single-Stage 6D Object Pose Estimation

arXiv 1911.08324 ↗First posted 19 Nov 2019cs.CVcited by 88

Not on the map. Why?

Abstract (arXiv)

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, however, is suboptimal: First, it is not end-to-end trainable. Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task. In this work, we introduce a deep architecture that directly regresses 6D poses from correspondences. It takes as input a group of candidate correspondences for each 3D keypoint and accounts for the fact that the order of the correspondences within each group is irrelevant, while the order of the groups, that is, of the 3D keypoints, is fixed. Our architecture is generic and can thus be exploited in conjunction with existing correspondence-extraction networks so as to yield single-stage 6D pose estimation frameworks. Our experiments demonstrate that these single-stage frameworks consistently outperform their two-stage counterparts in terms of both accuracy and speed.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 27; 2023: 23; 2024: 11; 2025: 10; 2026: 3.

88 papers.

Sort:

By area:

  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. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  4. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  5. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 113
  6. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  7. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  8. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  9. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  10. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  11. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  12. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
38 more
  1. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  2. 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  4. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  5. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  6. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  7. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  8. 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
  9. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  10. 2022Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimationcited by 22
  11. 2022Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraintscited by 21
  12. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  13. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  14. 2021StablePose: Learning 6D Object Poses from Geometrically Stable Patchescited by 17
  15. 2021PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimationcited by 17
  16. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  17. 2022YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regressioncited by 17
  18. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  19. 2021T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regressioncited by 16
  20. 2021Polarimetric Pose Predictioncited by 16
  21. 2023Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimationcited by 16
  22. 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
  23. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  24. 2021DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistencycited by 14
  25. 2022CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Spacecited by 13
  26. 2023Rigidity-Aware Detection for 6D Object Pose Estimationcited by 13
  27. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
  28. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  29. 20233D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimationcited by 11
  30. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  31. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  32. 2024RHOBIN Challenge: Reconstruction of Human Object Interactioncited by 10
  33. 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 10
  34. 2025GoTrack: Generic 6DoF Object Pose Refinement and Trackingcited by 10
  35. 2021DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimationcited by 9
  36. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictionscited by 9
  37. 2022DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimationcited by 9
  38. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9

50 most cited of 88 All 88 (JSON)