Research map / 3D vision / Human pose estimation
Estimating Egocentric 3D Human Pose in Global Space
Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Christian Theobalt
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 local pose optimizer (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 134.7 -> 119.5 | Improved |
| add global pose optimizer (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 123.1 -> 119.5 | Improved |
| add VAE motion prior (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 128.1 -> 119.5 | Improved |
| use sequential VAE instead of GMM prior (ablation) | Mo2Cap2+Ours · Our test set | PA-MPJPE: 90.12 -> 82.06 | Improved |
| use sequential VAE instead of single-frame VAE (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 122.2 -> 119.5 | Improved |
| use CNN-based VAE instead of VIBE RNN VAE (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 126.7 -> 119.5 | Improved |
| use CNN-based VAE instead of MEVA RNN VAE (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 121.6 -> 119.5 | Improved |
| use CNN-based VAE instead of VIBE RNN VAE (ablation) | optimization · Our test set | time per 10-frame segment: 552.1ms -> 195.7ms | Improved |
| use CNN-based VAE instead of MEVA RNN VAE (ablation) | optimization · Our test set | time per 10-frame segment: 1139.4ms -> 195.7ms | Improved |
| use CNN-based VAE instead of MLP VAE (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 122.2 -> 119.5 | Improved |
| use heatmap reprojection error instead of conventional reprojection (ablation) | Mo2Cap2+Ours · Our test set | Global MPJPE: 128.2 -> 119.5 | Improved |
| add our global optimization over SLAM projection | Mo2Cap2 · Our test set | Global MPJPE: 141.8 -> 119.5 | Improved |
Closest papers by meaning
- Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement (CVPR 2024 · similarity 0.90)
- 3D Human Pose Perception from Egocentric Stereo Videos (CVPR 2024 · similarity 0.87)
- EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024 · similarity 0.86)
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.86)
- Estimating Body and Hand Motion in an Ego-sensed World (CVPR 2025 · similarity 0.86)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · 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.
