Research map / 3D vision / Human pose estimation
EventEgo3D++: 3D Human Motion Capture from A Head-Mounted Event Camera
Christen Millerdurai, Hiroyasu Akada, Jian Wang, Diogo Carbonera Luvizon, Alain Pagani, Didier Stricker, Christian Theobalt, Vladislav Golyanik
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 segmentation decoder to the egocentric pose module (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 111.01 -> 108.85 | Improved |
| add frame buffer to propagate past events (ablation) | EventEgo3D++ with seg decoder · EE3D-R | MPJPE: 108.85 -> 107.58 | Improved |
| add confidence decoder (ablation) | EventEgo3D++ with seg decoder and frame buffer · EE3D-R | PA-MPJPE: 83.95 -> 79.66 | Improved |
| add 2D reprojection loss (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 107.30 -> 106.50 | Improved |
| add bone loss (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 106.50 -> 104.73 | Improved |
| add visibility mask for 3D and 2D joint supervision (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 104.73 -> 102.15 | Improved |
| add 2D reprojection loss (ablation) | EventEgo3D++ · EE3D-S | MPJPE: 100.80 -> 101.27 (PA-MPJPE 74.63 -> 72.76) | Mixed |
| add 2D reprojection loss (ablation) | EventEgo3D++ · EE3D-W | MPJPE: 177.28 -> 174.30 | Improved |
| add bone loss on top of 2D reprojection loss (ablation) | EventEgo3D++ · EE3D-W | MPJPE: 174.30 -> 166.19 | Improved |
| add bone loss on top of 2D reprojection loss (ablation) | EventEgo3D++ · EE3D-S | MPJPE: 101.27 -> 98.67 | Improved |
| add background event augmentation during EE3D-S pretraining (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 105.62 -> 102.15 | Improved |
| vary each loss weight by up to 10x (ablation) | EventEgo3D++ · EE3D-R | MPJPE: 102.15 vs 102.50 (bone length loss 0.001 vs 0.01) | No clear effect |
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.
- EventEgo3D — EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024) · better on 6 of 6 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
- EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024 · similarity 0.97)
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions (CVPR 2024 · similarity 0.85)
- Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement (CVPR 2024 · similarity 0.85)
- Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera (CVPR 2024 · similarity 0.85)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.85)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · 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.
