Research map / Video / Video generation
Relightful Video Portrait Harmonization
Jun Myeong Choi, Jae Shin Yoon, Luchao Qi, Roni Sengupta, Joon-Young Lee
Read the paperCheck 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 |
|---|---|---|---|
| add lighting deflickering of synthetic training data (Stage 2) (ablation) | HarmoVid · LUT test set | Motion Preservation: 0.9376 -> 0.5264 | Improved |
| add lighting deflickering of synthetic training data (Stage 2) (ablation) | HarmoVid · LUT test set | SSIM: 0.9187 -> 0.9306 | Improved |
| add dual-path real/synthetic training (Stage 3) (ablation) | HarmoVid · LUT test set | Motion Preservation: 0.5490 -> 0.5264 | Improved |
| add dual-path real/synthetic training (Stage 3) (ablation) | HarmoVid · LUT test set | SSIM: 0.9217 -> 0.9306 | Improved |
| add pseudo alpha mask in synthetic-to-real path (ablation) | HarmoVid · Boundary quality | Laplacian Variance: 66.106 -> 79.098 | Improved |
| add pseudo alpha mask in synthetic-to-real path (ablation) | HarmoVid · Boundary quality | Tenengrad: 2611.501 -> 3324.573 | Improved |
| use lighting deflickering network instead of general deflickerer BVD | video deflickering · Per-frame harmonization | Motion Preservation: 1.3439 -> 0.5395 | Improved |
| use lighting deflickering network instead of BVD | video deflickering · Per-frame LUT color jitter | CLIP Score: 0.9950 -> 0.9967 | Improved |
| HarmoVid vs Relightful Harmonization on SSIM | HarmoVid · LUT test set | SSIM: 0.9301 -> 0.9306 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Light-A-Video — Light-A-Video: Training-free Video Relighting via Progressive Light Fusion (ICCV 2025) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Relightful Harmonization: Lighting-aware Portrait Background Replacement (CVPR 2024 · similarity 0.92)
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization (CVPR 2025 · similarity 0.90)
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (CVPR 2025 · similarity 0.90)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.89)
- DreamLight: Towards Harmonious and Consistent Image Relighting (NeurIPS 2025 · similarity 0.88)
- High-Fidelity Relightable Monocular Portrait Animation with Lighting-Controllable Video Diffusion Model (CVPR 2025 · similarity 0.88)
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.
