mlsanityData to 14 Oct 2026

Deep Kinematic Pose Regression

arXiv 1609.05317 ↗First posted 17 Sep 2016cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose estimation, therefore requiring a post-processing to recover the correct geometry if desired, which is cumbersome and sub-optimal. In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation. The kinematic function is defined on the appropriately parameterized object motion variables. It is differentiable and can be used in the gradient descent based optimization in network training. The prior knowledge on the object geometric model is fully exploited and the structure is guaranteed to be valid. We show convincing experiment results on a toy example and the 3D human pose estimation problem. For the latter we achieve state-of-the-art result on Human3.6M dataset.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 8; 2023: 13; 2024: 3; 2025: 1.

40 papers.

Sort:

  1. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  2. 2021Neural Articulated Radiance Fieldcited by 196
  3. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  4. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 50
  5. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
  6. 2023I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactionscited by 44
  7. 2021Egocentric Pose Estimation from Human Vision Spancited by 27
  8. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  9. 2022Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimationcited by 25
  10. 2021BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Imagecited by 20
  11. 2023Scene-Aware 3D Multi-Human Motion Capture from a Single Cameracited by 19
  12. 2022MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenescited by 18
28 more
  1. 2021Real-time RGBD-based Extended Body Pose Estimationcited by 12
  2. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  3. 2021FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstructioncited by 11
  4. 2021GraFormer: Graph Convolution Transformer for 3D Pose Estimationcited by 10
  5. 2021Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutionscited by 6
  6. 20223D Human Pose Estimation Using M"obius Graph Convolutional Networkscited by 6
  7. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  8. 2022Enhancing Egocentric 3D Pose Estimation with Third Person Viewscited by 5
  9. 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
  10. 2021Learning Temporal 3D Human Pose Estimation with Pseudo-Labelscited by 4
  11. 2022PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimationcited by 4
  12. 2023Double-chain Constraints for 3D Human Pose Estimation in Images and Videoscited by 4
  13. 2021Learning Local Recurrent Models for Human Mesh Recoverycited by 3
  14. 2021PONet: Robust 3D Human Pose Estimation via Learning Orientations Onlycited by 2
  15. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimationcited by 2
  16. 2021On the role of depth predictions for 3D human pose estimationcited by 1
  17. 2022KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraintscited by 1
  18. 2023Self-supervised learning of object pose estimation using keypoint predictioncited by 1
  19. 2023Deep learning-based estimation of whole-body kinematics from multi-view imagescited by 1
  20. 2023Iterative Graph Filtering Network for 3D Human Pose Estimationcited by 1
  21. 2024Multi-hop graph transformer network for 3D human pose estimationcited by 1
  22. 2021Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstructioncited by 0
  23. 2022Supervised learning for improving the accuracy of robot-mounted 3D camera applied to human gait analysiscited by 0
  24. 2023Novel View Synthesis of Humans using Differentiable Renderingcited by 0
  25. 2023Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Posescited by 0
  26. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0
  27. 2024Occlusion Resilient 3D Human Pose Estimationcited by 0
  28. 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignmentcited by 0