mlsanityData to 14 Oct 2026

HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation

arXiv 2505.04276 ↗First posted 7 May 2025cs.CV cs.MMcited by 0

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

Abstract (arXiv)

We propose HDiffTG, a novel 3D Human Pose Estimation (3DHPE) method that integrates Transformer, Graph Convolutional Network (GCN), and diffusion model into a unified framework. HDiffTG leverages the strengths of these techniques to significantly improve pose estimation accuracy and robustness while maintaining a lightweight design. The Transformer captures global spatiotemporal dependencies, the GCN models local skeletal structures, and the diffusion model provides step-by-step optimization for fine-tuning, achieving a complementary balance between global and local features. This integration enhances the model's ability to handle pose estimation under occlusions and in complex scenarios. Furthermore, we introduce lightweight optimizations to the integrated model and refine the objective function design to reduce computational overhead without compromising performance. Evaluation results on the Human3.6M and MPI-INF-3DHP datasets demonstrate that HDiffTG achieves state-of-the-art (SOTA) performance on the MPI-INF-3DHP dataset while excelling in both accuracy and computational efficiency. Additionally, the model exhibits exceptional robustness in noisy and occluded environments. Source codes and models are available at https://github.com/CirceJie/HDiffTG

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 33 of its 40 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

33 of 40 references.

Closest ancestors · 3

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
  3. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models29 Nov

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  6. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  7. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  8. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  9. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  10. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  11. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  12. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
18 more
  1. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  2. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  3. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  4. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 92
  5. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  6. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  7. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  8. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  9. 2019Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsensecited by 71
  10. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 64
  11. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  12. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  13. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  14. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  15. 2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
  16. 2020A review of 3D human pose estimation algorithms for markerless motion capturecited by 24
  17. 2020Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videoscited by 23
  18. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  2. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
  3. 2025HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation
  4. 2025Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
  5. 2024D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
  6. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
  7. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
  8. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model