Research map / 3D vision / Human pose estimation
HybridCap: Inertia-Aid Monocular Capture of Challenging Human Motions
Read the paperCheck 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 |
|---|---|---|---|
| add the hierarchical inference module (ablation) | HybridCap · HCM | MPJPE: 136.5 -> 43.3 | Helped |
| add skip connections to the recurrent blocks (ablation) | HybridCap inference network · HCM | MPJPE: 54.5 -> 43.3 | Helped |
| add bone-length awareness (ablation) | HybridCap inference network · HCM | MPJPE: 65.8 -> 43.3 | Helped |
| add the hybrid optimization module (ablation) | HybridCap · HCM | MPJPE: 57.5 -> 43.3 | Helped |
| add inertial terms to optimization (ablation) | HybridCap · HCM | Accel error: 62.2 -> 17.9 | Helped |
| replace the hierarchical inference network with VIBE structure (ablation) | HybridCap inference network · HCM | MPJPE: 43.3 -> 75.4 | Hurt |
| replace the hierarchical inference network with TransPose structure (ablation) | HybridCap inference network · HCM | MPJPE: 43.3 -> 61.0 | Hurt |
| use 4 IMUs and RGB together rather than either single modality (ablation) | HybridCap input · HCM | MPJPE: 104.7 -> 43.3; 77.6 -> 43.3 | Helped |
| reduce aiding sensors from 4 IMUs to 2 IMUs (ablation) | HybridCap input · HCM | MPJPE: 43.3 -> 65.0 | Hurt |
| increase aiding sensors from 4 IMUs to 12 IMUs (ablation) | HybridCap input · HCM | MPJPE: 43.3 -> 36.1 | Helped |
Closest papers by meaning
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.89)
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions (CVPR 2024 · similarity 0.88)
- Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos (NeurIPS 2024 · similarity 0.87)
- Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors (CVPR 2024 · similarity 0.86)
- Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units (AAAI 2025 · similarity 0.86)
- FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments (AAAI 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.