Research map / 3D vision / Face and shape
A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment
Roberto Valle, Jose M. Buenaposada, Antonio Valdes, Luis Baumela
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 |
|---|---|---|---|
| add coarse-to-fine shape-constrained ERT instead of monolithic ERT (ablation) | DCFE · 300W public Full | NME (%) | No clear effect |
| use deep CNN initialization with ERT refinement instead of CNN-only RCN | DCFE · 300W public Full (pupils) | NME (%): 5.41 -> 4.55 | Improved |
| CNN initialization quality in very large pose/scale cases | DCFE · 300W public Challenging | NME (%): SHN 7.00 vs DCFE 7.54 | Hurt |
Closest papers by meaning
- Robust Face Alignment via Deep Progressive Reinitialization and Adaptive Error-driven Learning (TPAMI 2021 · similarity 0.90)
- Robust Face Alignment Using a Mixture of Invariant Experts (ECCV 2016 · similarity 0.89)
- A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection (CVPR 2017 · similarity 0.89)
- Direct Shape Regression Networks for End-to-End Face Alignment (CVPR 2018 · similarity 0.89)
- Brute-Force Facial Landmark Analysis With a 140,000-Way Classifier (AAAI 2018 · similarity 0.88)
- How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks) (ICCV 2017 · similarity 0.88)
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.
