Research map / 3D vision / Face and shape
Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting
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 dense 3DMM fitting with cascaded CNN regression and PAWF features | Large-pose face alignment · AFLW test | NME (%): 4.72 vs 8.04; 4.72 vs 6.26 | Helped |
| Use dense 3DMM fitting with pose-invariant features | Large-pose face alignment · AFW | MAPE: 7.43 vs 8.61; 7.43 vs 9.13; 7.43 vs 11.09 | Helped |
| Replace PAWF features with D3PF features (ablation) | Proposed face alignment method · AFLW test | NME (%): 4.72 -> 5.02 | Hurt |
| Add cheek landmarks to PAWF features (ablation) | Proposed face alignment method · AFLW test | NME (%): 5.19 -> 4.72 | Helped |
| Use PAWF features instead of a bounding-box-normalized extracted patch (ablation) | Proposed face alignment method · AFLW test | NME (%): 5.51 -> 5.19 | Helped |
| Add cheek landmarks and use PAWF rather than a bounding-box-normalized extracted patch (ablation) | Proposed face alignment method · AFLW test | NME (%): 5.51 -> 4.72 | Helped |
| Use PAWF features instead of D3PF features, with cheek landmarks (ablation) | Proposed face alignment method · AFW | MAPE: 7.83 -> 7.43 | Helped |
Closest papers by meaning
- Face Alignment Across Large Poses: A 3D Solution (CVPR 2016 · similarity 0.91)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.87)
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · similarity 0.87)
- DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment (CVPR 2023 · similarity 0.87)
- Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition (CVPR 2018 · similarity 0.87)
- Pose Adapted Shape Learning for Large-Pose Face Reenactment (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.