Research map / 3D vision / Face and shape
MVF-Net: Multi-View 3D Face Morphable Model Regression
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 |
|---|---|---|---|
| use multi-view 3DMM regression with rendered cross-view constraints | MVF-Net · MICC Florence INC | mean point-to-plane L2 error: 1.360 -> 1.220 | Helped |
| use multi-view 3DMM regression with rendered cross-view constraints | MVF-Net · MICC Florence IND | mean point-to-plane L2 error: 1.246 -> 1.228 | Helped |
| add photometric self-supervision without alignment loss (ablation) | MVF-Net supervised pretrained model · MICC Florence INC | mean point-to-plane L2 error: 1.266 -> 1.240 | Helped |
| add photometric self-supervision without alignment loss (ablation) | MVF-Net supervised pretrained model · MICC Florence IND | mean point-to-plane L2 error: 1.252 -> 1.252 | No clear effect |
| add optical-flow alignment self-supervision without photometric loss (ablation) | MVF-Net supervised pretrained model · MICC Florence INC | mean point-to-plane L2 error: 1.266 -> 1.227 | Helped |
| add optical-flow alignment self-supervision without photometric loss (ablation) | MVF-Net supervised pretrained model · MICC Florence IND | mean point-to-plane L2 error: 1.252 -> 1.245 | Helped |
| combine photometric and optical-flow alignment self-supervision (ablation) | MVF-Net supervised pretrained model · MICC Florence INC | mean point-to-plane L2 error: 1.266 -> 1.220 | Helped |
| combine photometric and optical-flow alignment self-supervision (ablation) | MVF-Net supervised pretrained model · MICC Florence IND | mean point-to-plane L2 error: 1.252 -> 1.228 | Helped |
| use optical-flow alignment loss in addition to photometric loss (ablation) | MVF-Net self-supervised training · inconsistent lighting across views | qualitative reconstruction quality | Helped |
Closest papers by meaning
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.92)
- MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction (CVPR 2019 · similarity 0.92)
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.92)
- Deep Facial Non-Rigid Multi-View Stereo (CVPR 2020 · similarity 0.91)
- Unsupervised Training for 3D Morphable Model Regression (CVPR 2018 · similarity 0.90)
- Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition (CVPR 2018 · similarity 0.90)
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.