mlsanityData to 14 Oct 2026

Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

arXiv 2305.15873 ↗First posted 25 May 2023cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Addressing pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the SE(3) group, marking the first application of diffusion models to SE(3) within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method's efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on SE(3). This formulation not only improves the convergence of denoising process but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 57 of its 77 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

57 of 77 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  12. 2022Video Diffusion Modelscited by 2,305
38 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  3. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  4. 2022Diffusion Models in Vision: A Surveycited by 1,015
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  6. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 499
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  8. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  11. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  12. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  13. 2022Diffsound: Discrete Diffusion Model for Text-to-sound Generationcited by 257
  14. 2022Diffusion Probabilistic Modeling for Video Generationcited by 238
  15. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  16. 2022Riemannian Score-Based Generative Modellingcited by 219
  17. 2023SE(3) diffusion model with application to protein backbone generationcited by 219
  18. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  19. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  20. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  21. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 149
  22. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  23. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  24. 2022SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusioncited by 127
  25. 2018A micro Lie theory for state estimation in roboticscited by 124
  26. 2020Normalizing Flows on Tori and Spherescited by 117
  27. 2020Neural Networks Fail to Learn Periodic Functions and How to Fix Itcited by 100
  28. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  29. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  30. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  31. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  32. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  33. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  34. 2020Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimationcited by 43
  35. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  36. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  37. 2020Learning Orientation Distributions for Object Pose Estimationcited by 18
  38. 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Predictioncited by 18

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 10; 2026: 3.

17 papers.

Sort:

By area:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  2. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  3. 2025Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Modelscited by 7
  4. 2025Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Modelscited by 5
  5. 2025RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimationcited by 4
  6. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  7. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
  8. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  9. 2025Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributionscited by 3
  10. 2024Precise Pick-and-Place using Score-Based Diffusion Networkscited by 1
  11. 2025Parallel Sampling of Diffusion Models on SO(3)cited by 1
  12. 2025Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Cloudscited by 1
5 more
  1. 2025Deterministic Object Pose Confidence Region Estimationcited by 0
  2. 2025LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusioncited by 0
  3. 2026Landscape-Awareness for Geometric View Diffusion Modelcited by 0
  4. 2026Towards a Modular Bin-picking Framework for Handling Object Pose Uncertaintiescited by 0
  5. 2026A Geometry-Driven, Framework-Agnostic Optimization for Object Pose Estimationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
  2. 2024Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion
  3. 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
  4. 2025Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
  5. 2024Object Pose Estimation via the Aggregation of Diffusion Features
  6. 2024Particle-based 6D Object Pose Estimation from Point Clouds using Diffusion Models
  7. 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation
  8. 2025MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation