mlsanityData to 14 Oct 2026

Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling

arXiv 2605.15583 ↗First posted 15 May 2026cs.CVcited by 0

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

Abstract (arXiv)

We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models (MDMs) pre-trained on large 2D human pose datasets. Specifically, we extend multi-view ancestral sampling of diffusion models to the task of 2D-3D lifting of human pose. To this end, we newly propose a conditional multi-view ancestral sampling (cMAS) that optimizes the 3D pose such that its multi-view projections follow the manifold in 2D MDM noise space, while conditioning the 3D pose to match the given 2D poses and anatomical constraints of humans. Experiments on the Yoga dataset demonstrate that our method achieves better cross-domain performance compared to state-of-the-art supervised and unsupervised 3D pose estimation methods, including extreme human poses where 3D supervision is unavailable. Code is available at: https://github.com/asaa0001/c-MAS.

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 36 of its 48 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

36 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion23 Oct

Other references · 35

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2022Human Motion Diffusion Modelcited by 1,080
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  5. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  6. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  7. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2023Human Motion Diffusion as a Generative Priorcited by 357
  11. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  12. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
23 more
  1. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 223
  2. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  3. 2023Object Motion Guided Human Motion Synthesiscited by 212
  4. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
  5. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  6. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  7. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  8. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  9. 2017Compositional Human Pose Regressioncited by 124
  10. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  11. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  12. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  13. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  14. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  15. 2023Single Motion Diffusioncited by 65
  16. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  17. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  18. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  19. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  20. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  21. 2015Direct Prediction of 3D Body Poses from Motion Compensated Sequencescited by 26
  22. 20233DYoga90: A Hierarchical Video Dataset for Yoga Pose Understandingcited by 3
  23. 2020SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regressioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
  2. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  3. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  4. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  5. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling
  6. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
  7. 2024Lifting Motion to the 3D World via 2D Diffusion
  8. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation