Research map / 3D vision / Face and shape
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 linear instead of nonlinear regressors (ablation) | joint alignment and reconstruction · BU3DFE 3D reconstruction | MAE: 1.92 -> 1.87 | Improved |
| use nonlinear (CNN feature, MLP) regressors instead of linear (ablation) | joint alignment and reconstruction · AFLW alignment | NME: 4.49 -> 4.16 | Improved |
| use nonlinear instead of linear regressors (ablation) | joint alignment and reconstruction · AFLW2000-3D alignment | NME: 4.61 -> 4.20 | Improved |
| fuse 3D shape matching with 2D matcher | CenterLoss · Multi-PIE exp. 1 (+-90 degrees) | accuracy (%): 48.2 -> 63.7 | Improved |
| fuse 3D shape matching with 2D matcher | LDF-Net · Multi-PIE exp. 1 (+-90 degrees) | accuracy (%): 65.3 -> 70.4 | Improved |
| fuse 3D shape matching with 2D matcher | VGG · Multi-PIE exp. 1 (avg) | accuracy (%): 79.5 -> 85.5 | Improved |
| fuse 3D shape matching with 2D matcher | LightenedCNN · Multi-PIE exp. 1 (avg) | accuracy (%): 68.8 -> 75.1 | Improved |
| fuse 3D shape matching with 2D matcher | CenterLoss · Multi-PIE exp. 1 (+-45 degrees) | accuracy (%): 98.8 -> 97.8 | Hurt |
| fuse 3D shape matching with 2D matcher | LDF-Net · Multi-PIE exp. 1 (avg) | accuracy (%): 90.2 -> 90.9 | Improved |
| fuse 3D shape matching with 2D matcher | CenterLoss · Multi-PIE exp. 2 (expressions, avg) | accuracy (%): 78.7 -> 81.4 | Improved |
| fuse 3D shape matching with 2D matcher | CenterLoss · CFP frontal-profile verification | accuracy (%): 69.27 -> 72.99 | Improved |
| fuse 3D shape matching with 2D matcher | CenterLoss · CFP frontal-frontal verification | accuracy (%): 86.43 -> 89.21 | Improved |
Closest papers by meaning
- Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression (ICCV 2017 · similarity 0.89)
- How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks) (ICCV 2017 · similarity 0.89)
- Faster Than Real-Time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses (ICCV 2017 · similarity 0.88)
- A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image (TPAMI 2017 · similarity 0.88)
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018 · similarity 0.88)
- FaceLift: Semi-supervised 3D Facial Landmark Localization (CVPR 2024 · similarity 0.86)
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.
