Research map / 3D vision / Human pose estimation
SimPoE: Simulated Character Control for 3D Human Pose Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Integrate kinematic inference with physics-based character control in a jointly learned policy | SimPoE · Human3.6M | MPJPE: 57.3 -> 56.7 | Helped |
| Integrate kinematic inference with physics-based character control in a jointly learned policy | SimPoE · In-House Motion Dataset | MPJPE: 36.7 -> 26.6 | Helped |
| Add meta-PD control to dynamically scale PD parameters (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | pose accuracy | Helped |
| Add the kinematic refinement unit using 2D keypoint evidence (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | pose accuracy | Helped |
| Add a residual connection from the refined kinematic pose to PD target angles (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | pose accuracy | Helped |
| Add residual forces and torques to the action (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | Accel | Helped |
| Add the feature extraction layer using current- and next-frame information (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | pose accuracy | Helped |
| Increase kinematic refinement iterations beyond about 5 (ablation) | SimPoE · Human3.6M and In-House Motion Dataset | pose accuracy | No clear effect |
Closest papers by meaning
- Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose From Monocular Video (CVPR 2022 · similarity 0.89)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.88)
- Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos (NeurIPS 2024 · similarity 0.88)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.87)
- InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint (NeurIPS 2024 · similarity 0.87)
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.