Research map / 3D vision / Face and shape
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
Read the paperCheck 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 |
|---|---|---|---|
| Use the Frankenstein model, including articulated hand modeling, instead of body-only SMPL | Frankenstein · Moving-person silhouette overlap | silhouette accuracy: 84.79% -> 85.91% | Helped |
| Add ICP point-cloud fitting | Frankenstein · Moving-person silhouette overlap | silhouette accuracy: 85.91% -> 87.68% | Helped |
| Replace Frankenstein with Adam while retaining ICP fitting | Frankenstein · Moving-person silhouette overlap | silhouette accuracy: 87.68% -> 87.74% | No clear effect |
| Use Adam, which learns clothing and hair shape variation from fitted people | Adam · Moving-person silhouette overlap | silhouette accuracy: 87.68% -> 87.74% | Mixed |
Closest papers by meaning
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.87)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.86)
- Expressive Forecasting of 3D Whole-Body Human Motions (AAAI 2024 · similarity 0.85)
- ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling (NeurIPS 2024 · similarity 0.85)
- Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning (CVPR 2025 · similarity 0.85)
- MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures (CVPR 2024 · similarity 0.85)
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.