mlsanityData to 14 Oct 2026

D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement

arXiv 2401.03914 ↗First posted 8 Jan 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Three-dimensional (3D) human pose estimation using a monocular camera has gained increasing attention due to its ease of implementation and the abundance of data available from daily life. However, owing to the inherent depth ambiguity in images, the accuracy of existing monocular camera-based 3D pose estimation methods remains unsatisfactory, and the estimated 3D poses usually include much noise. By observing the histogram of this noise, we find each dimension of the noise follows a certain distribution, which indicates the possibility for a neural network to learn the mapping between noisy poses and ground truth poses. In this work, in order to obtain more accurate 3D poses, a Diffusion-based 3D Pose Refiner (D3PRefiner) is proposed to refine the output of any existing 3D pose estimator. We first introduce a conditional multivariate Gaussian distribution to model the distribution of noisy 3D poses, using paired 2D poses and noisy 3D poses as conditions to achieve greater accuracy. Additionally, we leverage the architecture of current diffusion models to convert the distribution of noisy 3D poses into ground truth 3D poses. To evaluate the effectiveness of the proposed method, two state-of-the-art sequence-to-sequence 3D pose estimators are used as basic 3D pose estimation models, and the proposed method is evaluated on different types of 2D poses and different lengths of the input sequence. Experimental results demonstrate the proposed architecture can significantly improve the performance of current sequence-to-sequence 3D pose estimators, with a reduction of at least 10.3% in the mean per joint position error (MPJPE) and at least 11.0% in the Procrustes MPJPE (P-MPJPE).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 8 Jan 2024.

Builds on

29 of 48 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  9. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  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. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
17 more
  1. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  2. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  3. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  4. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 92
  5. 2017Exploiting temporal information for 3D pose estimationcited by 89
  6. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  7. 2022Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtubecited by 82
  8. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  9. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  10. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  11. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  12. 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
  13. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  14. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  15. 2017Recurrent 3D Pose Sequence Machinescited by 12
  16. 20183D human pose estimation from depth maps using a deep combination of posescited by 6
  17. 2022Deep Active Visual Attention for Real-time Robot Motion Generation: Emergence of Tool-body Assimilation and Adaptive Tool-usecited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  2. 2022DiffPose: Toward More Reliable 3D Pose Estimation
  3. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  4. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
  5. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
  6. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  7. 2025MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation
  8. 2023DPoser: Diffusion Model as Robust 3D Human Pose Prior