Research map / 3D vision / Face and shape
A Robust Multilinear Model Learning Framework for 3D Faces
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 |
|---|---|---|---|
| Jointly learn the multilinear model while completing missing shapes | RMM · BU-3DFE set and Bosphorus set | median reconstruction error | No clear effect |
| Jointly learn the multilinear model while completing missing shapes | RMM · Bosphorus set | median reconstruction error | Helped |
| Jointly learn the multilinear model while reconstructing corrupt scans | RMM · BU-3DFE set and Bosphorus set | reconstruction error | Helped |
| Use RMM to reconstruct corrupt scans | RMM · BU-3DFE set with 50% corrupt data | expression reconstruction | Hurt |
| Optimize expression labels | RMM · BU-3DFE set | components to keep 90% of data variability: 26 -> 20 | Helped |
| Optimize expression labels | RMM · Bosphorus set | components to keep 90% of data variability: 25 -> 15 | Helped |
| Add regularization to missing-shape completion (ablation) | RMM · BU-3DFE set and Bosphorus set | shape plausibility | Helped |
| Add the compactness term to corrupt-scan reconstruction (ablation) | RMM · BU-3DFE set and Bosphorus set | reconstruction quality | Helped |
| Add the regularization term to corrupt-scan reconstruction (ablation) | RMM · BU-3DFE set and Bosphorus set | artifacts in corrupt regions | Helped |
| Use the full objective, including compactness, data, and regularization terms (ablation) | RMM · BU-3DFE set and Bosphorus set | corrupt-scan reconstruction quality | Helped |
Closest papers by meaning
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.87)
- FML: Face Model Learning From Videos (CVPR 2019 · similarity 0.87)
- Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz (CVPR 2018 · similarity 0.87)
- Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation (CVPR 2023 · similarity 0.87)
- OFER: Occluded Face Expression Reconstruction (CVPR 2025 · similarity 0.85)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (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.