mlsanityData to 7 Oct 2026

Context Modeling in 3D Human Pose Estimation: A Unified Perspective

arXiv 2103.15507 ↗First posted 29 Mar 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Estimating 3D human pose from a single image suffers from severe ambiguity since multiple 3D joint configurations may have the same 2D projection. The state-of-the-art methods often rely on context modeling methods such as pictorial structure model (PSM) or graph neural network (GNN) to reduce ambiguity. However, there is no study that rigorously compares them side by side. So we first present a general formula for context modeling in which both PSM and GNN are its special cases. By comparing the two methods, we found that the end-to-end training scheme in GNN and the limb length constraints in PSM are two complementary factors to improve results. To combine their advantages, we propose ContextPose based on attention mechanism that allows enforcing soft limb length constraints in a deep network. The approach effectively reduces the chance of getting absurd 3D pose estimates with incorrect limb lengths and achieves state-of-the-art results on two benchmark datasets. More importantly, the introduction of limb length constraints into deep networks enables the approach to achieve much better generalization performance.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

27 of 43 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  11. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  12. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
15 more
  1. 2017Integral Human Pose Regressioncited by 255
  2. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  3. 2019Learnable Triangulation of Human Posecited by 160
  4. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  5. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  6. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  7. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  8. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  9. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  10. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  11. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  12. 2014Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relationscited by 24
  13. 2014Robust Estimation of 3D Human Poses from a Single Imagecited by 23
  14. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19
  15. 20143D Shape Estimation from 2D Landmarks: A Convex Relaxation Approachcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 7; 2024: 11; 2025: 5; 2026: 1.

37 papers.

Sort:

By area:

  1. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  2. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  3. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  4. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  5. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
  6. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  7. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  8. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  9. 2023Proactive Multi-Camera Collaboration For 3D Human Pose Estimationcited by 13
  10. 2023A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimationcited by 11
  11. 2022VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Datacited by 10
  12. 2022Dynamic Graph Reasoning for Multi-person 3D Pose Estimationcited by 9
25 more
  1. 2023LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Networkcited by 9
  2. 2025MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimationcited by 9
  3. 2022A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completioncited by 7
  4. 20223D Human Pose Estimation Using M"obius Graph Convolutional Networkscited by 6
  5. 2024GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correctioncited by 5
  6. 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimatorscited by 4
  7. 2024Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encodingcited by 3
  8. 2024Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimationcited by 2
  9. 2024An Animation-based Augmentation Approach for Action Recognition from Discontinuous Videocited by 2
  10. 2024Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Trainingcited by 2
  11. 2024FaceLift: Semi-supervised 3D Facial Landmark Localizationcited by 2
  12. 2024CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertaintycited by 2
  13. 2025Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimationcited by 2
  14. 2025PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotationcited by 2
  15. 2026ActionMap: Robot Policy Learning via Voxel Action Heatmapcited by 2
  16. 2022Decanus to Legatus: Synthetic training for 2D-3D human pose liftingcited by 1
  17. 2023Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuningcited by 1
  18. 2023VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR Datacited by 1
  19. 2024Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimationcited by 1
  20. 2021Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognitioncited by 0
  21. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0
  22. 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignmentcited by 0
  23. 2024Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimationcited by 0
  24. 2025PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimationcited by 0
  25. 2025PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimationcited by 0