Research map / 3D vision / Human pose estimation
EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices
Jiaxi Jiang, Bharat Bhatnagar, Nan Yang, Lingni Ma, Sebastian Starke, Robin Kips, Nadine Bertsch (Rueegg), Christian Holz, Federica Bogo
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 |
|---|---|---|---|
| combine ego and exo signals (vs ego-only) (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 7.53 -> 5.72 | Improved |
| add egocentric input to the exo pipeline (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 11.45 -> 5.72 | Improved |
| use EgoNet region proposals instead of YOLO boxes (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 6.43 -> 5.72 | Improved |
| add learned DINOv3 visibility gating (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 6.30 -> 5.72 | Improved |
| use DINO scores rather than ViTPose confidence (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 6.29 -> 5.72 | Improved |
| hard mask keypoints by ViTPose confidence (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJVE: 12.77 -> 15.31 (vs full model) | Hurt |
| add depth scaling of rays (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 6.26 -> 5.72 | Improved |
| transform rays into wearer head frame instead of world or observer space (ablation) | EgoExoMoCap · Nymeria (3-point) | MPJPE: 6.99 -> 5.72 (world); 6.14 -> 5.72 (exo) | Improved |
| use multiple observers instead of a single observer | EgoExoMoCap · EgoHumans multi-observer subset (3-point) | MPJPE: 8.80 -> 7.11 | Improved |
| learned fusion with confidence instead of triangulated keypoints for multi-view (ablation) | EgoExoMoCap · EgoHumans multi-observer subset (3-point) | MPJPE: 8.49 -> 7.11 | Improved |
| fuse PromptHMR and EgoPoser outputs naively | PromptHMR+EgoPoser · Nymeria (3-point) | MPJVE: 12.77 vs 17.49 | Hurt |
| RPM versus EgoExoMoCap on jitter | RPM · Nymeria (3-point) | Jitter: 1.29 vs 2.16 | Hurt |
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.
- AvatarPoser — AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing (ECCV 2022) · better on 2 of 2 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
- Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input (CVPR 2025 · similarity 0.90)
- Estimating Body and Hand Motion in an Ego-sensed World (CVPR 2025 · similarity 0.89)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.89)
- Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera (CVPR 2024 · similarity 0.88)
- HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations (CVPR 2024 · similarity 0.88)
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.87)
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.
