mlsanityData to 7 Oct 2026

DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

arXiv 2212.02796 ↗First posted 6 Dec 2022cs.CVcited by 29

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

Abstract (arXiv)

Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguities and occlusions. To handle this problem, many previous works exploit temporal information to mitigate such difficulties. However, there are many real-world applications where frame sequences are not accessible. This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. Rather than exploiting temporal information, we alleviate the depth ambiguity by generating multiple 3D pose candidates which can be mapped to an identical 2D keypoint. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. By considering the correlation between human joints by replacing the conventional denoising U-Net with graph convolutional network, our approach accomplishes further performance improvements. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets. Comprehensive experiments are conducted to prove the efficacy of the proposed method, and they confirm that our model outperforms state-of-the-art multi-hypothesis 3D HPE methods.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 46 of its 62 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

46 of 62 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2021Variational Diffusion Modelscited by 1,145
34 more
  1. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  2. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  4. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  5. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  9. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  10. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  11. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  12. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  13. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  14. 2017Compositional Human Pose Regressioncited by 124
  15. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  16. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  17. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  18. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  19. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  20. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  21. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  22. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  23. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  24. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  25. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  26. 20183D Human Pose Estimation in RGBD Images for Robotic Task Learningcited by 33
  27. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  28. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  29. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  30. 20183D Human Pose Estimation on a Configurable Bed from a Pressure Imagecited by 13
  31. 2020Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decompositioncited by 10
  32. 2020Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimationcited by 5
  33. 2021Characterizing Multidimensional Capacitive Servoing for Physical Human-Robot Interactioncited by 3
  34. 2020Simultaneous Learning from Human Pose and Object Cues for Real-Time Activity Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 12; 2025: 5; 2026: 4.

29 papers.

Sort:

By area:

  1. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  2. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 81
  3. 2023Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinementcited by 31
  4. 2023Parallel Vertex Diffusion for Unified Visual Groundingcited by 28
  5. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 26
  6. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 18
  7. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  8. 2024HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloudcited by 12
  9. 2025HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimationcited by 8
  10. 2023DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Modelscited by 7
  11. 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimatorscited by 4
  12. 2024PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modelingcited by 3
17 more
  1. 2023Denoising Diffusion for 3D Hand Pose Estimation from Imagescited by 2
  2. 2023Physics-Guided Human Motion Capture with Pose Probability Modelingcited by 2
  3. 2024Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Frameworkcited by 2
  4. 2024Diffusion-based Graph Generative Methodscited by 2
  5. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  6. 2025Benchmarking 3D Human Pose Estimation Models under Occlusionscited by 2
  7. 2025DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimationcited by 2
  8. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  9. 2024ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimationcited by 1
  10. 2024Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Videocited by 1
  11. 2025StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusioncited by 1
  12. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimationcited by 1
  13. 2026Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregationcited by 1
  14. 2024D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinementcited by 0
  15. 2024VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inferencecited by 0
  16. 2026GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimationcited by 0
  17. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  2. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  3. 2022DiffPose: Toward More Reliable 3D Pose Estimation
  4. 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser
  5. 2025HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation
  6. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
  7. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  8. 2026Flow Matching for Probabilistic Monocular 3D Human Pose Estimation