Research map / Image generation / Image restoration
Deep Fractional Fourier Transform
Hu Yu, Jie Huang, Lingzhi Li, Man Zhou, Feng Zhao
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 fractional-order (p=0.5) path to spatial-frequency convolution (MFRFC vs SFC) (ablation) | Faster RCNN · PASCAL VOC 2007 | mAP: 77.89 -> 77.96 | Improved |
| add fractional-order path (ablation) | ResNet · CIFAR-10 | accuracy (%): 95.34 -> 95.43 | Improved |
| add fractional-order path (ablation) | DnCNN · SIDD | PSNR: 37.3454 -> 37.6084 | Improved |
| add fractional-order path (ablation) | PReNet · Rain200H | PSNR: 29.498 -> 29.735 | Improved |
| add fractional-order path (ablation) | GridNet · SOTS indoor | PSNR: 32.97 -> 33.39 | Improved |
| add fractional-order path (ablation) | SID · LOL | PSNR: 21.9222 -> 22.3666 | Improved |
| add fractional-order path (ablation) | MSBDN · SOTS indoor | PSNR: 32.26 -> 32.45 | Improved |
| add spatial-frequency (SFC) operator to baseline (ablation) | DnCNN · SIDD | SSIM: 0.8904 -> 0.8866 | Hurt |
| replace baseline convolution with MFRFC | SID · LOL | PSNR: 20.1062 -> 22.3666 | Improved |
| replace baseline convolution with MFRFC | Faster RCNN · PASCAL VOC 2007 | mAP: 77.26 -> 77.96 | Improved |
| add SFC operator to baseline (ablation) | DRBN · LOL | SSIM: 0.8361 -> 0.8356 | No clear effect |
Closest papers by meaning
- Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing (AAAI 2025 · similarity 0.85)
- Frequency Dynamic Convolution for Dense Image Prediction (CVPR 2025 · similarity 0.85)
- Misalignment-Robust Frequency Distribution Loss for Image Transformation (CVPR 2024 · similarity 0.83)
- Visual Fourier Prompt Tuning (NeurIPS 2024 · similarity 0.83)
- Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting (NeurIPS 2024 · similarity 0.83)
- FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining (ICML 2025 · similarity 0.83)
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.
