Research map / 3D vision / Human pose estimation
D&D: Learning Human Dynamics from Dynamic Camera
Jiefeng Li, Siyuan Bian, Chao Xu, Gang Liu, Gang Yu, Cewu Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add inertial force control (explicit inertia modeling) (ablation) | D&D · 3DPW | MPJPE: 76.0 -> 73.7 | Improved |
| add inertial force control (ablation) | D&D · 3DPW | ACCEL: 10.0 -> 7.0 | Improved |
| add inertial force control (ablation) | D&D · Human3.6M | MPJPE: 53.8 -> 52.5 | Improved |
| add inertial force control (ablation) | D&D · Human3.6M | ACCEL: 6.7 -> 6.1 | Improved |
| add probabilistic contact torque (ablation) | D&D · 3DPW | ACCEL: 9.8 -> 7.0 | Improved |
| add probabilistic contact torque (ablation) | D&D · 3DPW | MPJPE: 74.6 -> 73.7 | Improved |
| add probabilistic contact torque (ablation) | D&D · Human3.6M | MPJPE: 53.4 -> 52.5 | Improved |
| add attentive PD controller over meta-PD controller (ablation) | D&D · 3DPW | ACCEL: 8.0 -> 7.0 | Improved |
| add attentive PD controller over meta-PD controller (ablation) | D&D · 3DPW | MPJPE: 73.8 -> 73.7 | No clear effect |
| add attentive PD controller over meta-PD controller (ablation) | D&D · Human3.6M | MPJPE: 52.5 -> 52.5 | No clear effect |
| predict physical properties instead of velocity (VelNet) (ablation) | D&D · 3DPW | MPJPE: 79.3 -> 73.7 | Improved |
| predict physical properties instead of acceleration (AccNet) (ablation) | D&D · Human3.6M | MPJPE: 90.1 -> 52.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SimPoE — SimPoE: Simulated Character Control for 3D Human Pose Estimation (CVPR 2021) · better on 4 of 5 shared results
- VIBE — VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Contact and Human Dynamics from Monocular Video (ECCV 2020 · similarity 0.92)
- Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos (NeurIPS 2024 · similarity 0.91)
- Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose From Monocular Video (CVPR 2022 · similarity 0.91)
- Learning 3D Human Dynamics From Video (CVPR 2019 · similarity 0.90)
- Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors (CVPR 2024 · similarity 0.88)
- PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos (CVPR 2024 · similarity 0.88)
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.
