Research map / Image generation / Editing and style transfer
Towards High Fidelity Face Relighting With Realistic Shadows
Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
Check 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 |
|---|---|---|---|
| Use ratio-image estimation instead of direct luminance estimation (ablation) | Face relighting model · Multi-PIE | MSE: 0.0343 -> 0.0292 | Improved |
| Add shadow-border weighted ratio losses (ablation) | Face relighting model · Multi-PIE | MSE: 0.0290 -> 0.0292 | Mixed |
| Add ambient-light estimation from shadow masks (ablation) | Face relighting model · Multi-PIE | MSE (face region): 0.0242 -> 0.0233 | Improved |
| Add face feature consistency loss (ablation) | Face relighting model · Multi-PIE | MSE: 0.0346 -> 0.0292 | Improved |
| Add gradient consistency loss (ablation) | Face relighting model · Multi-PIE | DSSIM: 0.1605 -> 0.1589 | Hurt |
| Add structural dissimilarity loss (ablation) | Face relighting model · Multi-PIE | DSSIM: 0.1703 -> 0.1605 | Improved |
| Add adversarial loss (ablation) | Face relighting model · Multi-PIE | MSE: 0.0361 -> 0.0292 | Improved |
| Use ratio-image relighting rather than direct luminance prediction | Face relighting model · Multi-PIE | Si-MSE: 0.0282 -> 0.0220 | Improved |
Closest papers by meaning
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces (CVPR 2025 · similarity 0.88)
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (CVPR 2025 · similarity 0.87)
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization (CVPR 2025 · similarity 0.86)
- Recasting Regional Lighting for Shadow Removal (AAAI 2024 · similarity 0.86)
- DreamLight: Towards Harmonious and Consistent Image Relighting (NeurIPS 2025 · similarity 0.86)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.86)
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.
