mlsanityData to 7 Oct 2026

Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation

arXiv 2303.11579 ↗First posted 21 Mar 2023cs.CVcited by 81

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D human pose estimation. On the one hand, D3DP generates multiple possible 3D pose hypotheses for a single 2D observation. It gradually diffuses the ground truth 3D poses to a random distribution, and learns a denoiser conditioned on 2D keypoints to recover the uncontaminated 3D poses. The proposed D3DP is compatible with existing 3D pose estimators and supports users to balance efficiency and accuracy during inference through two customizable parameters. On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use. It reprojects 3D pose hypotheses to the 2D camera plane, selects the best hypothesis joint-by-joint based on the reprojection errors, and combines the selected joints into the final pose. The proposed JPMA conducts aggregation at the joint level and makes use of the 2D prior information, both of which have been overlooked by previous approaches. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets show that our method outperforms the state-of-the-art deterministic and probabilistic approaches by 1.5% and 8.9%, respectively. Code is available at https://github.com/paTRICK-swk/D3DP.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 54 of its 72 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

54 of 72 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2015Variational Inference with Normalizing Flowscited by 2,161
  11. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
38 more
  1. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  3. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  4. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  5. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  7. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  9. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  13. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  14. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  15. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 195
  16. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  17. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  18. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 147
  19. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99
  20. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  21. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  22. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  23. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  24. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  25. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  26. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  27. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  28. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  29. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  30. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  31. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  32. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  33. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Datacited by 35
  34. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  35. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  36. 2020Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimationcited by 26
  37. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  38. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 32; 2025: 24; 2026: 13.

81 papers.

Sort:

By area:

  1. 2023MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusioncited by 37
  2. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 33
  3. 2023Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinementcited by 31
  4. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 29
  5. 2023SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generationcited by 26
  6. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  7. 2024Diffusion Model is a Good Pose Estimator from 3D RF-Visioncited by 21
  8. 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
  9. 2024Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observationcited by 16
  10. 2023Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Modelscited by 14
  11. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  12. 2024Attention-Propagation Network for Egocentric Heatmap to 3D Pose Liftingcited by 13
38 more
  1. 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoisercited by 13
  2. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humanscited by 13
  3. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  4. 2024HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloudcited by 12
  5. 2024Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Modelscited by 12
  6. 2024Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Networkcited by 12
  7. 2024Action Detection via an Image Diffusion Processcited by 11
  8. 2024EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modelingcited by 11
  9. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusioncited by 9
  10. 2025HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimationcited by 8
  11. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modelingcited by 7
  12. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  13. 2023ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimationcited by 6
  14. 2024GazeHTA: End-to-end Gaze Target Detection with Head-Target Associationcited by 6
  15. 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recoverycited by 6
  16. 2024Linguistics-Vision Monotonic Consistent Network for Sign Language Productioncited by 5
  17. 2025Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Modelscited by 5
  18. 2025H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformerscited by 5
  19. 20233DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusioncited by 4
  20. 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimatorscited by 4
  21. 2024PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modelingcited by 3
  22. 2024Diff-Reg v1: Diffusion Matching Model for Registration Problemcited by 3
  23. 2024Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimationcited by 3
  24. 2026FMPose3D: monocular 3D pose estimation via flow matchingcited by 3
  25. 2023DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detectioncited by 2
  26. 20243D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN Refinementcited by 2
  27. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  28. 2024DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Posecited by 2
  29. 2024BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustmentcited by 2
  30. 2024CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertaintycited by 2
  31. 2025Benchmarking 3D Human Pose Estimation Models under Occlusionscited by 2
  32. 2025PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networkscited by 2
  33. 2025DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimationcited by 2
  34. 2025RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Liftingcited by 2
  35. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  36. 2024Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaitoncited by 1
  37. 2024EPOCH: Jointly Estimating the 3D Pose of Cameras and Humanscited by 1
  38. 2024PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimationcited by 1

50 most cited of 81 All 81 (JSON)