Research map / Image generation / Editing and style transfer
Unsupervised Face Normalization With Extreme Pose and Expression in the Wild
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 |
|---|---|---|---|
| Apply FNM as preprocessing before VGG-Face | VGG-Face · IJB-A | Rank-1 identification: 92.8±0.8 -> 94.6±0.5 | Helped |
| Apply FNM as preprocessing before Light CNN | Light CNN · IJB-A | verification @FAR=0.001: 67.4±2.2 -> 83.8±2.6 | Helped |
| Apply FNM before Light CNN | Light CNN · Multi-PIE Setting-1, ±90° | Rank-1 recognition rate: 2.6 -> 55.8 | Helped |
| Add pixel-wise consistency loss Lp (ablation) | FNM+Light CNN · Multi-PIE Setting-1, ±90° | Rank-1 recognition rate: 46.9 -> 55.8 | Helped |
| Add face attention discriminators (ablation) | FNM+Light CNN · Multi-PIE Setting-1, ±90° | Rank-1 recognition rate: 41.3 -> 55.8 | Helped |
Closest papers by meaning
- Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement (CVPR 2021 · similarity 0.90)
- Face Normals "In-The-Wild" Using Fully Convolutional Networks (CVPR 2017 · similarity 0.89)
- Towards Pose Invariant Face Recognition in the Wild (CVPR 2018 · similarity 0.88)
- UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition (CVPR 2025 · similarity 0.86)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.86)
- UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition (ICLR 2025 · 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.