Research map / 3D vision / Human pose estimation
Scene-Aware Egocentric 3D Human Pose Estimation
Jian Wang, Diogo Luvizon, Weipeng Xu, Lingjie Liu, 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 scene-aware voxel features and scene geometry to egocentric pose estimation | EgoPW-style egocentric pose estimation · Our test dataset | MPJPE: 189.6 -> 118.5 | Improved |
| Add scene-aware voxel features and scene geometry to egocentric pose estimation | EgoPW-style egocentric pose estimation · Wang et al. test dataset | PA-MPJPE: 81.71 -> 76.50 | Improved |
| Add scene-aware voxel features and scene geometry to egocentric pose estimation | EgoPW-style egocentric pose estimation · Mo²Cap² test dataset | PA-MPJPE: 83.17 -> 79.65 | Improved |
| Add scene-aware voxel features and scene geometry to egocentric pose estimation | EgoPW-style egocentric pose estimation · Our test dataset | Contact: 38.8% -> 89.4% | Improved |
| Add scene depth input to the V2V pose network (ablation) | Scene-aware egocentric pose estimator · Our test dataset | MPJPE: 188.1 -> 118.5 | Improved |
| Use depth inpainting to recover scene depth behind the human body (ablation) | Scene-aware egocentric pose estimator · Our test dataset | MPJPE: 124.2 -> 118.5 | Improved |
| Use depth inpainting to recover scene depth behind the human body (ablation) | Scene depth estimator · Our test dataset | Abs-Rel: 0.3834 -> 0.1069 | Improved |
| Use ground-truth scene depth instead of estimated depth (ablation) | Scene-aware egocentric pose estimator · Our test dataset | MPJPE: 118.5 -> 109.9 | Improved |
| Represent image pose features and scene depth jointly in voxel space rather than simple concatenation (ablation) | Egocentric pose estimation · Our test dataset | MPJPE: 149.6 -> 118.5 | Improved |
| Add a scene-contact optimization term to EgoPW predictions (ablation) | EgoPW · Our test dataset | MPJPE: 187.1 vs 189.6 | No clear effect |
Closest papers by meaning
- Estimating Egocentric 3D Human Pose in the Wild With External Weak Supervision (CVPR 2022 · similarity 0.92)
- 3D Human Pose Perception from Egocentric Stereo Videos (CVPR 2024 · similarity 0.91)
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.90)
- Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting (CVPR 2024 · similarity 0.89)
- Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement (CVPR 2024 · similarity 0.89)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.88)
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.
