Research map / Video / Video generation
Neural Video Portrait Relighting in Real-Time via Consistency Modeling
Longwen Zhang, Qixuan Zhang, Minye Wu, Jingyi Yu, Lan Xu
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 structure self-supervision (content) (ablation) | Neural video portrait relighting · Synthesized sequences | RMSE: 0.0549 -> 0.0349 | Improved |
| add structure self-supervision (content) (ablation) | Neural video portrait relighting · Synthesized sequences | PSNR: 25.5496 -> 30.6110 | Improved |
| add temporal consistency modeling (ablation) | Neural video portrait relighting · Synthesized sequences | RMSE: 0.0404 -> 0.0349 | Improved |
| add temporal consistency modeling (ablation) | Neural video portrait relighting · Synthesized sequences | PSNR: 28.6403 -> 30.6110 | Improved |
| add semantic parsing multi-task (ablation) | Neural video portrait relighting · Synthesized sequences | RMSE: 0.0680 -> 0.0349 | Improved |
| add semantic parsing multi-task (ablation) | Neural video portrait relighting · Synthesized sequences | PSNR: 23.6189 -> 30.6110 | Improved |
| add Beta-based lighting sampling (ablation) | Neural video portrait relighting · Synthesized sequences | RMSE: 0.0616 -> 0.0349 | Improved |
| add Beta-based lighting sampling (ablation) | Neural video portrait relighting · Synthesized sequences | SSIM: 0.9223 -> 0.9584 | Improved |
| add temporal consistency modeling (ablation) | Neural video portrait relighting · Synthesized sequences | SSIM: 0.9510 -> 0.9584 | Improved |
| use proposed method instead of EMRCM (best baseline) | Neural video portrait relighting · Dynamic OLAT test set | PSNR: 22.7197 -> 30.6110 | Improved |
| use proposed method instead of SIPR | Neural video portrait relighting · Dynamic OLAT test set | SSIM: 0.8901 -> 0.9584 | Improved |
Closest papers by meaning
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (CVPR 2025 · similarity 0.91)
- Real-time 3D-aware Portrait Video Relighting (CVPR 2024 · similarity 0.90)
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization (CVPR 2025 · similarity 0.89)
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback (NeurIPS 2025 · similarity 0.88)
- DreamLight: Towards Harmonious and Consistent Image Relighting (NeurIPS 2025 · similarity 0.88)
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces (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.
