Research map / 3D vision / Depth and stereo
EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera
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 |
|---|---|---|---|
| Use event trajectories with hybrid batch optimization and event-based pose refinement instead of high-frame-rate RGB processing | EventCap · Ground-truth sequence | AE_all (mm): 98.4$\pm$22.8 -> 73.7$\pm$11.8 (Mono_all); 110.3$\pm$20.4 -> 73.7$\pm$11.8 (HMR_all) | Helped |
| Use EventCap instead of low-frame-rate pose estimation with linear upsampling | EventCap · Ground-truth sequence | AE_all (mm): 88.6$\pm${17.3} -> 73.7$\pm$11.8 (Mono_linear); 105.3$\pm$19.2 -> 73.7$\pm$11.8 (HMR_linear) | Helped |
| Use EventCap instead of reference-image HMR | EventCap · Ground-truth sequence | AE_all (mm): 83.5 -> 73.7 | Helped |
| Use EventCap instead of reference-image MonoPerfCap | EventCap · Ground-truth sequence | AE_all (mm): 76.5 -> 73.7 | Helped |
| Use event-based data instead of high-frame-rate image data | EventCap · Ground-truth sequence | Size_sec: 58.59 -> 2.02 | Helped |
| Add batch optimization combining CNN-based 2D/3D pose estimates and event trajectories (ablation) | EventCap · EventCap dataset | Average per-joint 3D error | Helped |
| Add event-based pose refinement (ablation) | EventCap · EventCap dataset | Average per-joint 3D error | Helped |
| Use a pre-scanned 3D template mesh instead of an estimated SMPL mesh (ablation) | EventCap · Ground-truth sequence | Average per-joint 3D error (AE): 77.88mm -> 73.72mm | Helped |
Closest papers by meaning
- EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024 · similarity 0.90)
- A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions (NeurIPS 2024 · similarity 0.86)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.86)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · similarity 0.85)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.84)
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions (CVPR 2024 · 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.