mlsanityData to 14 Oct 2026

Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data

arXiv 1812.00287 ↗First posted 1 Dec 2018cs.CVcited by 68

Not on the map. Why?

Abstract (arXiv)

3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. This ambiguity in both detection and pose estimation means that an object instance can be perfectly described by several different poses and even classes. In this work we propose to explicitly deal with this uncertainty. For each object instance we predict multiple pose and class outcomes to estimate the specific pose distribution generated by symmetries and repetitive textures. The distribution collapses to a single outcome when the visual appearance uniquely identifies just one valid pose. We show the benefits of our approach which provides not only a better explanation for pose ambiguity, but also a higher accuracy in terms of pose estimation.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 25; 2023: 17; 2024: 7; 2025: 9; 2026: 1.

68 papers.

Sort:

By area:

  1. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  2. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  3. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  4. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  5. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  6. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  7. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  8. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  9. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 58
  10. 2022HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarioscited by 53
  11. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  12. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
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 40
  4. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  5. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  6. 2022DPODv2: Dense Correspondence-Based 6 DoF Pose Estimationcited by 32
  7. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  8. 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
  9. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  10. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  11. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  12. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  13. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 18
  14. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  15. 2021Polarimetric Pose Predictioncited by 16
  16. 2021PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimationcited by 14
  17. 2021DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistencycited by 14
  18. 2023SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimationcited by 14
  19. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
  20. 2022Unseen Object 6D Pose Estimation: A Benchmark and Baselinescited by 12
  21. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  22. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  23. 20226D Robotic Assembly Based on RGB-only Object Pose Estimationcited by 9
  24. 2024Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimationcited by 9
  25. 2022Ki-Pode: Keypoint-based Implicit Pose Distribution Estimation of Rigid Objectscited by 7
  26. 2022Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulationcited by 6
  27. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 6
  28. 2023Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distributioncited by 5
  29. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  30. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  31. 2022Spatial Feature Mapping for 6DoF Object Pose Estimationcited by 3
  32. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
  33. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  34. 2025Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributionscited by 3
  35. 2022CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimationcited by 2
  36. 2022Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labelscited by 2
  37. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2
  38. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2

50 most cited of 68 All 68 (JSON)