mlsanityData to 14 Oct 2026

Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation

arXiv 2306.17074 ↗First posted 29 Jun 2023cs.CV cs.AIcited by 5

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

Abstract (arXiv)

One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vision Transformers. In this paper, we propose DiffusionPose, a new scheme that formulates 2D HPE as a keypoints heatmaps generation problem from noised heatmaps. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps with respect to conditions constructed by image feature. During inference, the diffusion model generates heatmaps from initialized heatmaps in a progressive denoising way. Moreover, we further explore improving the performance of DiffusionPose with conditions from human structural information. Extensive experiments show the prowess of our DiffusionPose, with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets, respectively.

Key facts. Cited by 5 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 48 of its 55 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

48 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models29 Nov

Other references · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2022Video Diffusion Modelscited by 2,305
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2019Objects as Pointscited by 1,175
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  12. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
35 more
  1. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 499
  4. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  5. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  6. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  7. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  8. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  9. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  10. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  11. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  12. 2022DaViT: Dual Attention Vision Transformerscited by 175
  13. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  14. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  15. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  16. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  17. 2020TransPose: Keypoint Localization via Transformercited by 126
  18. 2017Compositional Human Pose Regressioncited by 124
  19. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  20. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  21. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
  22. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  23. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99
  24. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  25. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  26. 2022DiffusionInst: Diffusion Model for Instance Segmentationcited by 49
  27. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  28. 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
  29. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  30. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 32
  31. 2020Peeking into occluded joints: A novel framework for crowd pose estimationcited by 25
  32. 2022Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolutioncited by 25
  33. 2018Learning to Refine Human Pose Estimationcited by 19
  34. 2022Multi-Tailed Vision Transformer for Efficient Inferencecited by 10
  35. 2022I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 1.

5 papers.

  1. 2024Diffusion Model is a Good Pose Estimator from 3D RF-Visioncited by 22
  2. 2023DPoser: Diffusion Model as Robust 3D Human Pose Priorcited by 17
  3. 2024FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenescited by 10
  4. 2023Guided Diffusion from Self-Supervised Diffusion Featurescited by 9
  5. 2025Refinement Module based on Parse Graph for Human Pose Estimationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
  2. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
  3. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  4. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  5. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
  6. 2025SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation
  7. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
  8. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation