# Deep Kinematic Pose Regression

arXiv: https://arxiv.org/abs/1609.05317 · HTML: https://mlsanity.com/paper/1609.05317/

## Key facts

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

## Built on by (most cited first, 30 of 40)

- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)
- [UmeTrack: Unified multi-view end-to-end hand tracking for VR](https://mlsanity.com/paper/2211.00099/) (2022)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions](https://mlsanity.com/paper/2312.08869/) (2023)
- [Egocentric Pose Estimation from Human Vision Span](https://mlsanity.com/paper/2104.05167/) (2021)
- [KAMA: 3D Keypoint Aware Body Mesh Articulation](https://mlsanity.com/paper/2104.13502/) (2021)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image](https://mlsanity.com/paper/2105.09936/) (2021)
- [Scene-Aware 3D Multi-Human Motion Capture from a Single Camera](https://mlsanity.com/paper/2301.05175/) (2023)
- [MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes](https://mlsanity.com/paper/2208.08439/) (2022)
- [Real-time RGBD-based Extended Body Pose Estimation](https://mlsanity.com/paper/2103.03663/) (2021)
- [PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.09678/) (2023)
- [FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction](https://mlsanity.com/paper/2105.01937/) (2021)
- [GraFormer: Graph Convolution Transformer for 3D Pose Estimation](https://mlsanity.com/paper/2109.08364/) (2021)
- [Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions](https://mlsanity.com/paper/2103.03170/) (2021)
- [3D Human Pose Estimation Using M"obius Graph Convolutional Networks](https://mlsanity.com/paper/2203.10554/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Enhancing Egocentric 3D Pose Estimation with Third Person Views](https://mlsanity.com/paper/2201.02017/) (2022)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Learning Temporal 3D Human Pose Estimation with Pseudo-Labels](https://mlsanity.com/paper/2110.07578/) (2021)
- [PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation](https://mlsanity.com/paper/2204.11548/) (2022)
- [Double-chain Constraints for 3D Human Pose Estimation in Images and Videos](https://mlsanity.com/paper/2308.05298/) (2023)
- [Learning Local Recurrent Models for Human Mesh Recovery](https://mlsanity.com/paper/2107.12847/) (2021)
- [PONet: Robust 3D Human Pose Estimation via Learning Orientations Only](https://mlsanity.com/paper/2112.11153/) (2021)
- [FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation](https://mlsanity.com/paper/2512.14162/) (2025)
- [On the role of depth predictions for 3D human pose estimation](https://mlsanity.com/paper/2103.02521/) (2021)
- [KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints](https://mlsanity.com/paper/2207.12841/) (2022)
- [Self-supervised learning of object pose estimation using keypoint prediction](https://mlsanity.com/paper/2302.07360/) (2023)

## 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.