mlsanityData to 14 Oct 2026

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

arXiv 2508.00599 ↗First posted 1 Aug 2025cs.CVcited by 13

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

Abstract (arXiv)

We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of high-quality whole-body pose datasets. To address these limitations, we introduce a Diffusion model as body Pose prior (DPoser) and extend it to DPoser-X for expressive whole-body human pose modeling. Our approach unifies various pose-centric tasks as inverse problems, solving them through variational diffusion sampling. To enhance performance on downstream applications, we introduce a novel truncated timestep scheduling method specifically designed for pose data characteristics. We also propose a masked training mechanism that effectively combines whole-body and part-specific datasets, enabling our model to capture interdependencies between body parts while avoiding overfitting to specific actions. Extensive experiments demonstrate DPoser-X's robustness and versatility across multiple benchmarks for body, hand, face, and full-body pose modeling. Our model consistently outperforms state-of-the-art alternatives, establishing a new benchmark for whole-body human pose prior modeling.

Key facts. Cited by 13 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 40 of its 48 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

40 of 48 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models5 Aug
  2. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models29 Nov
  3. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  12. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
25 more
  1. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 405
  2. 2023Human Motion Diffusion as a Generative Priorcited by 357
  3. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  5. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
  6. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  7. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  8. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  9. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  10. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 222
  11. 2021Character Controllers Using Motion VAEscited by 184
  12. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  13. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
  14. 2022Towards Metrical Reconstruction of Human Facescited by 166
  15. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 155
  16. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 139
  17. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  18. 2023EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modelingcited by 105
  19. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 104
  20. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  21. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  22. 2021Adversarial Parametric Pose Priorcited by 38
  23. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  24. 2024NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priorscited by 27
  25. 2024Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modelingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 12.

13 papers.

Sort:

By area:

  1. 2026DuoMo: Dual Motion Diffusion for World-Space Human Reconstructioncited by 7
  2. 2026ViPS: Video-informed Pose Spaces for Auto-Rigged Meshescited by 3
  3. 2025Affordance-Guided Diffusion Prior for 3D Hand Reconstructioncited by 2
  4. 2026AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimationcited by 2
  5. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  6. 2026PDF-HR: Pose Distance Fields for Humanoid Robotscited by 1
  7. 2026Anny-Fit: All-Age Human Mesh Recoverycited by 1
  8. 2026Egocentric Whole-Body Human Mesh Recovery with Prior-Guided Learningcited by 1
  9. 2026FactorizedHMR: A Hybrid Framework for Video Human Mesh Recoverycited by 0
  10. 2026ARAPDiffusion: ARAP Regularization for Diffusion-Based Deformable Shape Space Learningcited by 0
  11. 2026PFM-HR: Pose Flow Matching for Humanoid Robotscited by 0
  12. 2026Promptable Animal Pose Tracking Across Speciescited by 0
1 more
  1. 2026ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wildcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DPoser: Diffusion Model as Robust 3D Human Pose Prior
  2. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  3. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  4. 2024PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
  5. 2025Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
  6. 2025LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusion
  7. 2024Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior
  8. 2022DiffPose: Toward More Reliable 3D Pose Estimation