Research map / Image generation / Super-resolution
Deep Blind Video Super-Resolution
Jinshan Pan, Haoran Bai, Jiangxin Dong, Jiawei Zhang, Jinhui Tang
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 motion blur estimation and intermediate latent image restoration (ablation) | Blind video SR network · REDS (4 test videos, x4) | PSNR: 30.18 -> 30.51 | Improved |
| add motion blur estimation compared with bicubic-upsampled inputs (ablation) | Blind video SR network · REDS (4 test videos, x4) | PSNR: 30.48 -> 30.51 | Improved |
| add motion blur estimation (ablation) | Blind video SR network · REDS (4 test videos, x4) | SSIM: 0.8609 -> 0.8674 | Improved |
| estimate blur kernel with network instead of fixed Gaussian kernel (ablation) | Blind video SR network · REDS kernel accuracy | PSNR: 25.48 -> 42.06 | Improved |
| estimate blur kernel with network instead of variational method of Ma et al. (ablation) | Blind video SR network · REDS kernel accuracy | PSNR: 31.24 -> 42.06 | Improved |
| compare with EDVR (no blur modelling, larger model) | Blind video SR network · REDS (4 test videos, x4) | PSNR: 31.07 -> 30.51 | Hurt |
| compare with DUF | Blind video SR network · Vid4 (x4) | PSNR: 25.84 -> 25.35 | Hurt |
| compare with DUF | Blind video SR network · SPMCS (x4) | PSNR: 29.31 -> 29.54 | Improved |
Closest papers by meaning
- Self-Supervised Deep Blind Video Super-Resolution (TPAMI 2024 · similarity 0.91)
- Learning the Non-Differentiable Optimization for Blind Super-Resolution (CVPR 2021 · similarity 0.90)
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI 2016 · similarity 0.90)
- Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · similarity 0.90)
- Blind Super-Resolution With Iterative Kernel Correction (CVPR 2019 · similarity 0.90)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · 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.
