Research map / 3D vision / Face and shape
Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz
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 |
|---|---|---|---|
| add learned shape and reflectance correctives to the 3DMM base (ablation) | Ours · Validation set | photometric error mean: 0.092 -> 0.072 | Helped |
| use a linear rather than nonlinear corrective space (ablation) | Ours · in-the-wild face images | reconstruction quality | Helped |
| jointly learn the multi-level face model with the regressor | Ours · in-the-wild faces with out-of-subspace appearance | reconstruction quality | Helped |
| use the proposed method instead of Tewari et al. [60] | face reconstruction · Volker sequence | geometric error mean: 2.94 mm -> 1.77 mm | Helped |
Closest papers by meaning
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.94)
- FML: Face Model Learning From Videos (CVPR 2019 · similarity 0.91)
- InverseFaceNet: Deep Monocular Inverse Face Rendering (CVPR 2018 · similarity 0.90)
- Monocular Identity-Conditioned Facial Reflectance Reconstruction (CVPR 2024 · similarity 0.88)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.88)
- OFER: Occluded Face Expression Reconstruction (CVPR 2025 · 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.