mlsanityData to 14 Oct 2026

GenPose: Generative Category-level Object Pose Estimation via Diffusion Models

arXiv 2306.10531 ↗First posted 18 Jun 2023cs.CVcited by 48

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches encounter challenges with partially observed point clouds, known as the multihypothesis issue. In this study, we propose a novel solution by reframing categorylevel object pose estimation as conditional generative modeling, departing from traditional point-to-point regression. Leveraging score-based diffusion models, we estimate object poses by sampling candidates from the diffusion model and aggregating them through a two-step process: filtering out outliers via likelihood estimation and subsequently mean-pooling the remaining candidates. To avoid the costly integration process when estimating the likelihood, we introduce an alternative method that trains an energy-based model from the original score-based model, enabling end-to-end likelihood estimation. Our approach achieves state-of-the-art performance on the REAL275 dataset, surpassing 50% and 60% on strict 5d2cm and 5d5cm metrics, respectively. Furthermore, our method demonstrates strong generalizability to novel categories sharing similar symmetric properties without fine-tuning and can readily adapt to object pose tracking tasks, yielding comparable results to the current state-of-the-art baselines.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 41 of its 53 references that are in the map. First posted on arXiv 18 Jun 2023.

Builds on

41 of 53 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2017Mask R-CNNcited by 7,277
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2023Consistency Modelscited by 1,822
  8. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  9. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  10. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  11. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  12. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
29 more
  1. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  2. 2020Learning Gradient Fields for Shape Generationcited by 245
  3. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  4. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 220
  5. 2022Riemannian Score-Based Generative Modellingcited by 219
  6. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  7. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  8. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  9. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  10. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  11. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  12. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 101
  13. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  14. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 84
  15. 2021Score-Based Point Cloud Denoisingcited by 83
  16. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  17. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  18. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  19. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  20. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  21. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  22. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 50
  23. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  24. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  25. 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
  26. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  27. 2021iCaps: Iterative Category-level Object Pose and Shape Estimationcited by 23
  28. 2022Generative Category-Level Shape and Pose Estimation with Semantic Primitivescited by 19
  29. 2023Proactive Multi-Camera Collaboration For 3D Human Pose Estimationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 28; 2026: 9.

48 papers.

Sort:

By area:

  1. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 50
  2. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 25
  3. 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 25
  4. 2025NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigationcited by 25
  5. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 18
  6. 2025SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Modelcited by 17
  7. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  8. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  9. 2023PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environmentscited by 11
  10. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 10
  11. 2025Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objectscited by 9
  12. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8
36 more
  1. 2023LVDiffusor: Distilling Functional Rearrangement Priors from Large Models into Diffusorcited by 7
  2. 2025Target-Aware Video Diffusion Modelscited by 7
  3. 2025CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulationcited by 7
  4. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  5. 2024Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Imagescited by 5
  6. 2025Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Modelscited by 5
  7. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 5
  8. 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Imagecited by 5
  9. 2025DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Modelscited by 4
  10. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 4
  11. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  12. 2025BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimationcited by 3
  13. 2025You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Graspingcited by 3
  14. 2024Conditional Variational Autoencoders for Probabilistic Pose Regressioncited by 2
  15. 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priorscited by 2
  16. 2025Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single Viewcited by 2
  17. 2026DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spacescited by 2
  18. 2025Foundation Feature-Driven Online End-Effector Pose Estimation: A Marker-Free and Learning-Free Approachcited by 1
  19. 2025OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real Worldcited by 1
  20. 2025Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimationcited by 1
  21. 2024OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGBcited by 0
  22. 2024Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusioncited by 0
  23. 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generationcited by 0
  24. 2025DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarioscited by 0
  25. 2025GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexitycited by 0
  26. 2025Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perceptioncited by 0
  27. 2025UniTac2Pose: A Unified Approach Learned in Simulation for Category-level Visuotactile In-hand Pose Estimationcited by 0
  28. 2025KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generationcited by 0
  29. 2026Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimationcited by 0
  30. 2026Exploring 6D Object Pose Estimation with Deformationcited by 0
  31. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0
  32. 2026UniPose9D: Universal Category-Agnostic Object Pose Estimationcited by 0
  33. 2026PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimationcited by 0
  34. 2026Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Modelscited by 0
  35. 2026LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimationcited by 0
  36. 2026FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022A Visual Navigation Perspective for Category-Level Object Pose Estimation
  2. 2024Learning a Category-level Object Pose Estimator without Pose Annotations
  3. 2024Object Pose Estimation via the Aggregation of Diffusion Features
  4. 2025SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation
  5. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  6. 2024Particle-based 6D Object Pose Estimation from Point Clouds using Diffusion Models
  7. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation
  8. 2024Can Generative Video Models Help Pose Estimation?