mlsanityData to 14 Oct 2026

HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation

arXiv 2508.14431 ↗First posted 20 Aug 2025cs.CVcited by 0

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

Abstract (arXiv)

Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing skeleton structure information, which can negatively impact the accuracy of pose estimation. To address these challenges, this paper introduces a novel 3D pose estimation method, HyperDiff, which integrates diffusion models with HyperGCN. The diffusion model effectively captures data uncertainty, alleviating depth ambiguity and occlusion. Meanwhile, HyperGCN, serving as a denoiser, employs multi-granularity structures to accurately model high-order correlations between joints. This improves the model's denoising capability especially for complex poses. Experimental results demonstrate that HyperDiff achieves state-of-the-art performance on the Human3.6M and MPI-INF-3DHP datasets and can flexibly adapt to varying computational resources to balance performance and efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 35 of its 46 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

35 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models8 May
  2. 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser7 Mar

Other references · 33

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  8. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  9. 2018Hypergraph Neural Networkscited by 488
  10. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  11. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  12. 2016Convolutional Pose Machinescited by 325
21 more
  1. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  2. 2019Hypergraph Convolution and Hypergraph Attentioncited by 228
  3. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
  6. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  7. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  8. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  9. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  10. 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
  11. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  12. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  13. 2020Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusioncited by 39
  14. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 34
  15. 2022GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimationcited by 21
  16. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  17. 2021Hierarchical Graph Networks for 3D Human Pose Estimationcited by 12
  18. 2022KEMP: Keyframe-Based Hierarchical End-to-End Deep Model for Long-Term Trajectory Predictioncited by 11
  19. 2023Regular Splitting Graph Network for 3D Human Pose Estimationcited by 11
  20. 2021Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognitioncited by 9
  21. 2023Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimationcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
  2. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  3. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
  4. 2022DiffPose: Toward More Reliable 3D Pose Estimation
  5. 2024D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
  6. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  7. 2025HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
  8. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation