Research map / Image generation / Super-resolution
FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks
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 |
|---|---|---|---|
| Apply FSR to FSRCNN | FSRCNN · TEST2K ×4 | PSNR: 25.61 -> 25.83 | Helped |
| Apply FSR to FSRCNN | FSRCNN · TEST4K ×4 | PSNR: 26.90 -> 27.01 | Helped |
| Apply FSR to CARN | CARN · TEST2K ×4 | PSNR: 25.95 -> 26.17 | Helped |
| Apply FSR to CARN | CARN · TEST8K ×4 | PSNR: 33.18 -> 33.20 | Hurt |
| Apply FSR to SRResNet | SRResNet · TEST2K ×4 | PSNR: 26.19 -> 26.31 | Helped |
| Apply FSR to SRResNet | SRResNet · TEST8K ×4 | PSNR: 33.50 -> 33.47 | Hurt |
| Apply FSR to RCAN | RCAN · TEST2K ×4 | PSNR: 26.39 -> 26.39 | No clear effect |
| Apply FSR to RCAN | RCAN · TEST4K ×4 | PSNR: 27.89 -> 27.89 | No clear effect |
| Add TABlock (ablation) | FSR-FSRCNN · TEST2K | PSNR: 25.78 -> 25.83 | Helped |
| Add TABlock (ablation) | FSR-FSRCNN · TEST4K | PSNR: 26.95 -> 27.01 | Helped |
| Add TABlock (ablation) | FSR-FSRCNN · TEST8K | PSNR: 32.58 -> 32.75 | Helped |
| Add SCBlock (ablation) | FSR-FSRCNN · TEST2K | PSNR: 25.77 -> 25.83 | Helped |
Closest papers by meaning
- Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution (AAAI 2021 · similarity 0.91)
- ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic (CVPR 2021 · similarity 0.90)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 2024 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.87)
- Exploring the Low-Pass Filtering Behavior in Image Super-Resolution (ICML 2024 · similarity 0.87)
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.