Research map / 3D vision / Face and shape
MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction
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 ICP pose refinement at resolution 128 instead of using the parametric-network pose estimate alone (ablation) | MMFace · AFLW2000-3D | NME68_2D mean: 6.11 -> 3.56 | Helped |
| Add ICP pose refinement at resolution 128 instead of using the parametric-network pose estimate alone (ablation) | MMFace · AFLW2000-3D | NME3D: 8.29 -> 3.78 | Helped |
| Increase ICP refinement resolution from 64 to 128 (ablation) | MMFace · AFLW2000-3D | NME68_2D mean: 3.90 -> 3.56 | Helped |
| Increase ICP refinement resolution from 64 to 128 (ablation) | MMFace · AFLW2000-3D | NME3D: 4.23 -> 3.78 | Helped |
| Increase ICP refinement resolution from 128 to 192 (ablation) | MMFace · AFLW2000-3D | NME68_2D mean: 3.56 -> 3.46 | Helped |
| Increase ICP refinement resolution from 128 to 192 (ablation) | MMFace · AFLW2000-3D | NME3D: 3.78 -> 3.66 | Helped |
| Replace estimated pose with ground-truth pose (ablation) | MMFace · AFLW2000-3D | NME68_2D mean: 3.56 -> 1.61 | Helped |
| Replace estimated pose with ground-truth pose (ablation) | MMFace · AFLW2000-3D | NME3D: 3.78 -> 2.01 | Helped |
Closest papers by meaning
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · similarity 0.92)
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.90)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.90)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.89)
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.89)
- Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition (CVPR 2018 · 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.