Research map / 3D vision / Human pose estimation
Simultaneous Facial Landmark Detection, Pose and Deformation Estimation Under Facial Occlusion
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 |
|---|---|---|---|
| jointly estimate facial landmarks, head pose, deformation, and occlusion instead of estimating landmarks alone (ablation) | COFW landmark detection · COFW | normalized landmark error: 7.70 -> 6.40 | Helped |
| add occlusion prediction to landmark detection (ablation) | cascade regression landmark detector · COFW | normalized landmark error: 7.70 -> 6.61 | Helped |
| add head pose and facial deformation information to the occlusion-aware landmark detector (ablation) | ours occlusion · COFW | normalized landmark error: 6.61 -> 6.40 | Helped |
| use the proposed method for continuous head pose estimation | head pose estimation · BU head tracking database | mean absolute error (average): 4.6 -> 4.4 | Helped |
| use the proposed method for yaw estimation | head pose estimation · MultiPIE | yaw mean absolute error: 5.31 -> 5.36 | No clear effect |
| use the proposed method for facial landmark detection | landmark detector · MultiPIE near-frontal | average pixel error: 4.09 -> 3.51 | Helped |
| use the proposed method for facial landmark detection across poses | landmark detector · MultiPIE all poses | average pixel error: 4.39 -> 3.50 | Helped |
| use the proposed method for occlusion prediction | facial occlusion predictor · COFW | recall at precision 80%: 37.0% -> 44.43% | Helped |
Closest papers by meaning
- Unsupervised Discovery of Facial Landmarks and Head Pose (CVPR 2025 · similarity 0.88)
- Towards Accurate Facial Landmark Detection via Cascaded Transformers (CVPR 2022 · similarity 0.87)
- Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks (CVPR 2019 · similarity 0.87)
- Brute-Force Facial Landmark Analysis With a 140,000-Way Classifier (AAAI 2018 · similarity 0.86)
- Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection (CVPR 2016 · similarity 0.86)
- Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network (CVPR 2017 · similarity 0.85)
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.