Research map / Image generation / Super-resolution
Flow-Based Kernel Prior With Application to Blind Super-Resolution
Check 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 |
|---|---|---|---|
| Replace the KernelGAN deep linear generator with FKP | KernelGAN · DIV2K ×2 | kernel PSNR: 44.95 -> 47.78 | Helped |
| Replace the KernelGAN deep linear generator with FKP | KernelGAN · DIV2K ×4 | non-blind PSNR: 23.69 -> 25.46 | Helped |
| Use FKP instead of the parametric Gaussian kernel prior | DIP · BSD100 ×2 | kernel PSNR: 34.99 -> 46.79 | Helped |
| Use FKP instead of the parametric Gaussian kernel prior | DIP · BSD100 ×2 | image PSNR before non-blind SR: 26.76/0.7091 -> 26.72/0.7089 | No clear effect |
| Replace the KernelGAN generator with FKP | KernelGAN · DIV2K ×2, non-Gaussian kernel | non-blind PSNR: 27.00 -> 27.40 | Helped |
| Replace the KernelGAN generator with FKP | KernelGAN · DIV2K ×2, image noise level 10 | non-blind PSNR: 28.53 -> 29.58 | Helped |
| Use FKP rather than an untrained parametric network kernel prior | DIP · BSD100 ×2, non-Gaussian kernel | kernel PSNR: 34.50 -> 44.27 | Helped |
Closest papers by meaning
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · similarity 0.91)
- Blind Super-Resolution With Iterative Kernel Correction (CVPR 2019 · similarity 0.89)
- Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · similarity 0.88)
- Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution (NeurIPS 2021 · similarity 0.88)
- KernelFusion: Zero-Shot Blind Super-Resolution via Patch Diffusion (ICLR 2026 · similarity 0.88)
- Boosting Flow-based Generative Super-Resolution Models via Learned Prior (CVPR 2024 · 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.