mlsanityData to 14 Oct 2026

ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation

arXiv 2312.06386 ↗First posted 11 Dec 2023cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose ManiPose, a manifold-constrained multi-hypothesis model for human-pose 2D-to-3D lifting. We provide theoretical and empirical evidence that, due to the depth ambiguity inherent to monocular 3D human pose estimation, traditional regression models suffer from pose-topology consistency issues, which standard evaluation metrics (MPJPE, P-MPJPE and PCK) fail to assess. ManiPose addresses depth ambiguity by proposing multiple candidate 3D poses for each 2D input, each with its estimated plausibility. Unlike previous multi-hypothesis approaches, ManiPose forgoes generative models, greatly facilitating its training and usage. By constraining the outputs to lie on the human pose manifold, ManiPose guarantees the consistency of all hypothetical poses, in contrast to previous works. We showcase the performance of ManiPose on real-world datasets, where it outperforms state-of-the-art models in pose consistency by a large margin while being very competitive on the MPJPE metric.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

40 of 55 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  4. 2017End-to-end Recovery of Human Shape and Posecited by 885
  5. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  6. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  12. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
28 more
  1. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  2. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  3. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2015Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networkscited by 139
  6. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  7. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  8. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 97
  9. 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
  10. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  11. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  12. 2017Exploiting temporal information for 3D pose estimationcited by 89
  13. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  14. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  15. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  16. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  17. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  18. 2016Stochastic Multiple Choice Learning for Training Diverse Deep Ensemblescited by 77
  19. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  20. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  21. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  22. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  23. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  24. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  25. 2017Confident Multiple Choice Learningcited by 24
  26. 2023Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysiscited by 12
  27. 2020DiverseNet: When One Right Answer is not Enoughcited by 11
  28. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026Flow Matching for Probabilistic Monocular 3D Human Pose Estimationcited by 2
  2. 2025Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mappingcited by 0
  3. 20253D Human Pose and Shape Estimation from LiDAR Point Clouds: A Reviewcited by 0
  4. 2026RPGD: RANSAC-P3P Gradient Descent for Extrinsic Calibration in 3D Human Pose Estimationcited by 0
  5. 2026SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistencycited by 0
  6. 2026CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Imagecited by 0