Research map / 3D vision / Depth and stereo
Force From Motion: Decoding Physical Sensation in a First Person Video
Hyun Soo Park, jyh-Jing Hwang, Jianbo Shi
Check 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 |
|---|---|---|---|
| Use CNN image cues and aggregate predictions with reconstructed camera orientations | Gravity direction estimation · First-person sport videos | gravity prediction error: ×2 ∼×10 | Improved |
| Recover physical scale using banked-turn torque equilibrium | 3D camera motion reconstruction · 11 sequences | scale ratio to IMU: 1.0188 median, 1.1613 mean, and 0.7003 std. | Improved |
| Decompose motion into active forces and passive forces using rigid-body dynamics | Active force identification · Controlled mountain biking | active action recognition | Improved |
| Estimate control inputs through inverse dynamics and bundle adjustment | Camera wearer angular motion · 11 scenes | angular velocity correlation with gyroscope: 0.87 mean correlation | Improved |
Closest papers by meaning
- PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos (CVPR 2024 · similarity 0.87)
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals (NeurIPS 2025 · similarity 0.86)
- Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos (NeurIPS 2024 · similarity 0.85)
- Seeing the Wind from a Falling Leaf (NeurIPS 2025 · similarity 0.85)
- ImDy: Human Inverse Dynamics from Imitated Observations (ICLR 2025 · similarity 0.85)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.84)
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.
