Research map / Image generation / Editing and style transfer
Synthesizing Normalized Faces From Facial Identity Features
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 |
|---|---|---|---|
| Add morph-based data augmentation to the 1K-image training set (ablation) | Face normalization decoder · LFW | visual fidelity | Helped |
| Use a CNN rather than a fully connected texture decoder (ablation) | Face normalization decoder · LFW | texture detail | Helped |
| Decouple landmark and texture prediction, then warp the texture to the predicted landmarks (ablation) | Face normalization decoder · Test data | reconstruction detail | Helped |
| Add the FaceNet embedding loss (ablation) | Face normalization decoder · LFW | identity preservation: all ... pass; without, about 2% ... would be mid-identified | Helped |
| Use identity features to synthesize normalized faces instead of directly warping the input image | FaceNet-based face normalization · LFW | robustness to pose, lighting, expression, and occlusion | Helped |
Closest papers by meaning
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.87)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.86)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.86)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.85)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.85)
- Neural Implicit Morphing of Face Images (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.
