Research map / 3D vision / Face and shape
Combining 3D Morphable Models: A Large Scale Face-And-Head Model
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 Gaussian-process regression refinement to the combined model (ablation) | CFHM-GP · Head shape estimation, fitted facial meshes | AUC: 0.681 -> 0.751 | Helped |
| Add Gaussian-process regression refinement to the combined model (ablation) | CFHM-GP · Head shape estimation, fitted facial meshes | Failure Rate (%): 7.55 -> 3.64 | Helped |
| Add Gaussian-process regression refinement to the combined model (ablation) | CFHM-GP · Head shape estimation, actual ground truth 3D facial meshes | AUC: 0.844 -> 0.880 | Helped |
| Add Gaussian-process regression refinement to the combined model (ablation) | CFHM-GP · Head shape estimation, actual ground truth 3D facial meshes | Failure Rate (%): 2.46 -> 0.62 | Helped |
| Combine the detailed LSFM face model with the full-head LYHM model | CFHM-ref · Head shape estimation, fitted facial meshes | AUC: 0.605 -> 0.751 | Helped |
| Combine the detailed LSFM face model with the full-head LYHM model | CFHM-ref · Head shape estimation, fitted facial meshes | Failure Rate (%): 19.21 -> 3.64 | Helped |
| Combine the detailed LSFM face model with the full-head LYHM model | CFHM-ref · Head shape estimation, actual ground truth 3D facial meshes | AUC: 0.739 -> 0.880 | Helped |
| Combine the detailed LSFM face model with the full-head LYHM model | CFHM-ref · Head shape estimation, actual ground truth 3D facial meshes | Failure Rate (%): 14.10 -> 0.62 | Helped |
| Refine combined models using regression-based rather than Gaussian-process combination (ablation) | CFHM-reg · Head shape estimation, actual ground truth 3D facial meshes | Failure Rate (%): 1.69 vs 2.46 | Mixed |
| Use a refined combined model rather than the demographic-specific refined models | CFHM-ref · Head model generalization | generalization error | Helped |
Closest papers by meaning
- A 3D Morphable Model Learnt From 10,000 Faces (CVPR 2016 · similarity 0.91)
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.90)
- 3D Face Morphable Models "In-The-Wild" (CVPR 2017 · similarity 0.89)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.88)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.88)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (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.