Research map / 3D vision / Human pose estimation
EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices
Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo, Siyu Tang
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 |
|---|---|---|---|
| fine-tune on EgoBody training set | SPIN · EgoBody test set | MPJPE: 182.8 -> 106.5 | Improved |
| fine-tune on EgoBody training set | METRO · EgoBody test set | MPJPE: 153.1 -> 98.5 | Improved |
| fine-tune on EgoBody training set | EFT · EgoBody test set | MPJPE: 123.9 -> 102.1 | Improved |
| fine-tune on EgoBody training set | SPIN · You2Me | PA-MPJPE: 152.8 -> 87.9 | Improved |
| fine-tune on EgoBody training set | EFT · You2Me | PA-MPJPE: 95.8 -> 85.6 | Improved |
| fine-tune on EgoBody training set | METRO · You2Me | PA-MPJPE: 117.7 -> 88.2 | Improved |
| fine-tune on EgoBody training set (robustness to blur) | SPIN · EgoBody test set | std over sharpness levels: 27.3 to 2.4 | Improved |
| fine-tune on EgoBody training set (robustness to blur) | EFT · EgoBody test set | std over sharpness levels: 11.1 to 1.3 | Improved |
| add motion blur augmentation when fine-tuning on original data (ablation) | SPIN · EgoBody test set | MPJPE: 182.8 -> 184.9 | Hurt |
| add aggressive crop augmentation / pretraining (EFT vs SPIN) | SPIN-architecture · EgoBody test set | MPJPE: 182.8 -> 123.9 | Improved |
| egocentric images versus third-person (3DPW) test | SoTA 3DHPS methods · EgoBody vs 3DPW | 3D joint error: 77% higher | Hurt |
| heavy motion blur (sharpness < 10) | SoTA 3DHPS methods · EgoBody test set | MPJPE | Hurt |
Later papers that compared with this method
1 later accepted paper reports Egobody3M as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR (CVPR 2026 · better on 6 of 6 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SPIN — SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (AAAI 2021) · better on 4 of 4 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
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.91)
- EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views (NeurIPS 2024 · similarity 0.91)
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.90)
- Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data (NeurIPS 2024 · similarity 0.90)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.89)
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos (CVPR 2025 · similarity 0.89)
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.
