mlsanityData to 14 Oct 2026

Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows

arXiv 2107.13788 ↗First posted 29 Jul 2021cs.CVcited by 85

Not on the map. Why?

Abstract (arXiv)

3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these ambiguities and only estimate a single solution. In contrast, we generate a diverse set of hypotheses that represents the full posterior distribution of feasible 3D poses. To this end, we propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. Additionally, uncertain detections and occlusions are effectively modeled by incorporating uncertainty information of the 2D detector as condition. Further keys to success are a learned 3D pose prior and a generalization of the best-of-M loss. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics. The implementation is available on GitHub.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 29 Jul 2021.

Builds on

37 of 56 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2015Variational Inference with Normalizing Flowscited by 2,170
  4. 2016Density estimation using Real NVPcited by 2,042
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  7. 2017End-to-end Recovery of Human Shape and Posecited by 885
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  9. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  10. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  11. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  12. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
25 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  3. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  4. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  5. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
  6. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  7. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  8. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 172
  9. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  10. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  11. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  12. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  13. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  14. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  15. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  16. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  17. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  18. 2020PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Timecited by 50
  19. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  20. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  21. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  22. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  23. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  24. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19
  25. 2017A Kinematic Chain Space for Monocular Motion Capturecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 19; 2023: 22; 2024: 24; 2025: 8; 2026: 8.

85 papers.

Sort:

By area:

  1. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  2. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  3. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  6. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  7. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  8. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  9. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  10. 2021Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wildcited by 48
  11. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  12. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
38 more
  1. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  2. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 34
  3. 2023Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Viewscited by 33
  4. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  5. 2024NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priorscited by 27
  6. 2023The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detectorcited by 25
  7. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  8. 2023HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimationcited by 24
  9. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  10. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  11. 20222D Human Pose Estimation: A Surveycited by 21
  12. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 21
  13. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  14. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  15. 2023Markerless human pose estimation for biomedical applications: a surveycited by 13
  16. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humanscited by 13
  17. 2025Towards Balanced Multi-Modal Learning in 3D Human Pose Estimationcited by 12
  18. 2023A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimationcited by 11
  19. 2024EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modelingcited by 11
  20. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  21. 2023On the Calibration of Human Pose Estimationcited by 10
  22. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  23. 2022Dynamic Graph Reasoning for Multi-person 3D Pose Estimationcited by 9
  24. 2022Self-supervised Human Mesh Recovery with Cross-Representation Alignmentcited by 9
  25. 2022VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimationcited by 9
  26. 2022Progressive Multi-view Human Mesh Recovery with Self-Supervisioncited by 9
  27. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusioncited by 9
  28. 2023Self-supervised 3D Human Pose Estimation from a Single Imagecited by 8
  29. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  30. 2022MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Viewscited by 7
  31. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  32. 2023The voraus-AD Dataset for Anomaly Detection in Robot Applicationscited by 7
  33. 2022Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributionscited by 6
  34. 2022Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledgecited by 6
  35. 2023ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimationcited by 6
  36. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  37. 2022HandFlow: Quantifying View-Dependent 3D Ambiguity in Two-Hand Reconstruction with Normalizing Flowcited by 5
  38. 2024Quantum Normalizing Flows for Anomaly Detectioncited by 5

50 most cited of 85 All 85 (JSON)