Research map / 3D vision / Human pose estimation
Monocular Total Capture: Posing Face, Body, and Hands in the Wild
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the newly captured 3D dataset to Human3.6M training data (ablation) | The pose-estimation network · Human3.6M | MPJPE (mm): 65.6 -> 60.9 | Helped |
| Add COCO 2D pose annotations to training data (ablation) | The pose-estimation network trained with Human3.6M and the new dataset · Human3.6M | MPJPE (mm): 60.9 -> 58.3 | Helped |
| Add the pose prior (ablation) | The proposed method · Human3.6M | MPJPE (mm): 58.3 -> 64.5 | Hurt |
| Use the proposed method with ground-truth root-depth alignment | Frankenstein hand model · Dexter+Object | AUC: 0.70 -> 0.84 | Helped |
| Use ground-truth root-depth alignment for evaluation | The proposed method and prior hand-pose methods · Dexter+Object | AUC: 0.70 -> 0.84; 0.71 -> 0.70 | Mixed |
| Apply texture-based temporal refinement (ablation) | The per-frame mesh fitting results · Panoptic Studio sequences | Temporal stability | Helped |
| Use the pose prior (ablation) | The proposed method · In-the-wild motion capture | Surface structure and joint-angle plausibility | Helped |
Closest papers by meaning
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · similarity 0.91)
- Monocular Real-Time Full Body Capture With Inter-Part Correlations (CVPR 2021 · similarity 0.91)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.89)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.89)
- Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement (CVPR 2024 · similarity 0.88)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · 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.