Research map / Video / Video segmentation and tracking
Video Face Super-Resolution with Motion-Adaptive Feedback Cell
Read the paperCheck 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 |
|---|---|---|---|
| Use MAFN instead of the strongest baseline for each input-frame setting | VSR · VoxCeleb testing, T=3 | PSNR: 34.38 -> 34.15 | Hurt |
| Use MAFN instead of the strongest baseline for each input-frame setting | VSR · VoxCeleb testing, T=5 | PSNR: 33.67 -> 34.59 | Helped |
| Use MAFN instead of the strongest baseline for each input-frame setting | VSR · VoxCeleb testing, T=7 | PSNR: 33.91 -> 34.81 | Helped |
| Add MAFC to the basic network (ablation) | MAFN · VoxCeleb testing, T=3 | PSNR: 32.48 -> 34.15 | Helped |
| Add MAFC to the basic network (ablation) | MAFN · VoxCeleb testing, T=5 | PSNR: 32.64 -> 34.59 | Helped |
| Add MAFC to the basic network (ablation) | MAFN · VoxCeleb testing, T=7 | PSNR: 32.55 -> 34.81 | Helped |
| Use both signal screen and compensation estimation units instead of signal screen alone (ablation) | MAFN · VoxCeleb testing, T=3 | PSNR: 33.89 -> 34.15 | Helped |
| Use both signal screen and compensation estimation units instead of signal screen alone (ablation) | MAFN · VoxCeleb testing, T=5 | PSNR: 34.20 -> 34.59 | Helped |
| Use both signal screen and compensation estimation units instead of signal screen alone (ablation) | MAFN · VoxCeleb testing, T=7 | PSNR: 34.37 -> 34.81 | Helped |
| Use both signal screen and compensation estimation units instead of compensation estimation alone (ablation) | MAFN · VoxCeleb testing, T=3 | PSNR: 33.82 -> 34.15 | Helped |
| Use both signal screen and compensation estimation units instead of compensation estimation alone (ablation) | MAFN · VoxCeleb testing, T=5 | PSNR: 33.11 -> 34.59 | Helped |
| Use both signal screen and compensation estimation units instead of compensation estimation alone (ablation) | MAFN · VoxCeleb testing, T=7 | PSNR: 33.29 -> 34.81 | Helped |
Closest papers by meaning
- Frame-Recurrent Video Super-Resolution (CVPR 2018 · similarity 0.92)
- Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation (CVPR 2018 · similarity 0.91)
- Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling (AAAI 2021 · similarity 0.90)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.89)
- Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution (CVPR 2025 · similarity 0.86)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 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.