Research map / 3D vision / Human pose estimation
Unsupervised Discovery of Facial Landmarks and Head Pose
Read the paperCheck 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 semantic-guided landmark localization instead of zero-shot initialization (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Forward NME: 2.82 -> 2.76 | Helped |
| Use semantic-guided landmark localization instead of zero-shot initialization (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | MAE: 5.62 -> 5.28 | Helped |
| Add image-aware text embedding adapter (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Forward NME: 2.86 -> 2.76 | Helped |
| Add image-aware text embedding adapter (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | MAE: 5.54 -> 5.28 | Helped |
| Use pose-based batching instead of randomized batches (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Pitch MAE: 8.20 -> 6.09 | Helped |
| Add rotate-and-render augmentation (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Forward NME: 3.01 -> 2.76 | Helped |
| Add rotate-and-render augmentation (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Pitch MAE: 6.78 -> 6.09 | Helped |
| Add rotate-and-render augmentation and pose-based batching (ablation) | Unsupervised facial landmark and head pose estimation · AFLW2000 | Forward NME: 3.05 -> 2.76 | Helped |
Closest papers by meaning
- Continuous Landmark Detection With 3D Queries (CVPR 2023 · similarity 0.88)
- LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood (CVPR 2020 · similarity 0.88)
- Learning to Detect 3D Facial Landmarks via Heatmap Regression with Graph Convolutional Network (AAAI 2022 · similarity 0.88)
- FaceLift: Semi-supervised 3D Facial Landmark Localization (CVPR 2024 · similarity 0.88)
- Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery (CVPR 2024 · similarity 0.86)
- Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024 · 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.