Research map / Image generation / Super-resolution
Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution
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 |
|---|---|---|---|
| Add OR-Net's frequency decomposition and region-adaptive aggregation | RealSR models · DRealSR ×2 | PSNR: 34.45 -> 34.56 | Helped |
| Add OR-Net's frequency decomposition and region-adaptive aggregation | RealSR models · DRealSR ×3 | PSNR: 33.06 -> 33.28 | Helped |
| Add OR-Net's frequency decomposition and region-adaptive aggregation | RealSR models · DRealSR ×4 | PSNR: 32.42 -> 32.59 | Helped |
| Add OR-Net's frequency decomposition and region-adaptive aggregation | RealSR models · RealSR ×2 | PSNR: 33.96 -> 34.08 | Helped |
| Add RFA (ablation) | OR-Net with FEU · DRealSR ×4 | PSNR: 32.34 -> 32.59 | Helped |
| Add FEU (ablation) | OR-Net with RFA · DRealSR ×4 | PSNR: 32.23 -> 32.59 | Helped |
| Add RFA and FEU (ablation) | OR-Net without both modules · DRealSR ×4 | PSNR: 32.11 -> 32.59 | Helped |
| Replace spatial attention with dynamic-convolution RFA (ablation) | OR-Net frequency aggregation · DRealSR ×4 | PSNR: 32.46 -> 32.59 | Helped |
| Increase frequency branches from 1 to 2 (ablation) | OR-Net FD · DRealSR ×4 | PSNR: 32.25 -> 32.40 | Helped |
| Increase frequency branches from 2 to 3 (ablation) | OR-Net FD · DRealSR ×4 | PSNR: 32.40 -> 32.59 | Helped |
| Increase frequency branches from 3 to 4 (ablation) | OR-Net FD · DRealSR ×4 | PSNR: 32.59 -> 32.52 | Hurt |
| Use three frequency branches rather than one (ablation) | OR-Net FD · DRealSR ×4 | PSNR: 32.25 -> 32.59 | Helped |
Closest papers by meaning
- FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks (AAAI 2023 · similarity 0.91)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.86)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.86)
- Exploring the Low-Pass Filtering Behavior in Image Super-Resolution (ICML 2024 · similarity 0.86)
- Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World (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.