mlsanityData to 14 Oct 2026

Compositional Human Pose Regression

arXiv 1704.00159 ↗First posted 1 Apr 2017cs.CVcited by 124

Not on the map. Why?

Abstract (arXiv)

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 25; 2023: 22; 2024: 23; 2025: 8; 2026: 8.

124 papers.

Sort:

By area:

  1. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  2. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  3. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  4. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  5. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  6. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  7. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  8. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  9. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 65
  10. 2023PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulationcited by 56
  11. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  12. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
38 more
  1. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
  2. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  3. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  4. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  5. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 41
  6. 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
  7. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  8. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  9. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  10. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  11. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  12. 2022DART: Articulated Hand Model with Diverse Accessories and Rich Texturescited by 25
  13. 2021A Survey on Human-aware Robot Navigationcited by 24
  14. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  15. 2023Ego3DPose: Capturing 3D Cues from Binocular Egocentric Viewscited by 22
  16. 20222D Human Pose Estimation: A Surveycited by 21
  17. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  18. 2023Scene-Aware 3D Multi-Human Motion Capture from a Single Cameracited by 19
  19. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  20. 2023From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understandingcited by 19
  21. 2021Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimationcited by 18
  22. 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Modelcited by 17
  23. 2021Real-time RGBD-based Extended Body Pose Estimationcited by 12
  24. 2021Hierarchical Graph Networks for 3D Human Pose Estimationcited by 12
  25. 2022HiFECap: Monocular High-Fidelity and Expressive Capture of Human Performancescited by 12
  26. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  27. 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Camerascited by 12
  28. 2023Regular Splitting Graph Network for 3D Human Pose Estimationcited by 11
  29. 2023Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wildcited by 11
  30. 2021GraFormer: Graph Convolution Transformer for 3D Pose Estimationcited by 10
  31. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  32. 2022Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimationcited by 10
  33. 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregationcited by 10
  34. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  35. 2022Dynamic Graph Reasoning for Multi-person 3D Pose Estimationcited by 9
  36. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  37. 2023Scene-aware Human Pose Generation using Transformercited by 9
  38. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusioncited by 9

50 most cited of 124 All 124 (JSON)