Research map / Image generation / Image restoration
Efficient Frequency-Domain Image Deraining with Contrastive Regularization
Ning Gao, Xingyu Jiang, Xiuhui Zhang, Yue Deng
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 FCR to training (ablation) | FADformer · Rain200H | PSNR (dB): 30.25 -> 30.73 | Improved |
| add FCR to training (ablation) | FADformer · DDN-Data | PSNR (dB): 33.51 -> 33.61 | Improved |
| add FCR to training (ablation) | MPRNet · Rain200H | PSNR (dB): 30.32 -> 30.62 | Improved |
| add FCR to dehazing training (ablation) | FFA-Net · SOTS-Indoor | PSNR (dB): 36.39 -> 37.29 | Improved |
| use frequency-domain contrastive regularization instead of VGG perceptual contrastive loss (ablation) | FADformer · Rain200H | PSNR (dB): 30.53 -> 30.73 | Improved |
| include negative samples in frequency regularization (ablation) | FADformer · Rain200H | PSNR (dB): 30.48 -> 30.73 | Improved |
| use too many negative samples (1:6 instead of 1:2) (ablation) | FCR · Rain200H | PSNR (dB): 30.73 -> 30.67 | Hurt |
| replace self-attention (MDTA) token mixer with FFCM (ablation) | FADformer · Rain200H | PSNR (dB): 29.66 -> 29.95 at depth {2,3,4,3,2} | Improved |
| add FFT/IFFT frequency branch to FFCM (ablation) | FFCM · Rain200H | PSNR (dB): 29.27 -> 30.73 | Improved |
| replace PGFN with plain DFN (no prior) (ablation) | FADformer · Rain200H | PSNR (dB): 30.34 -> 30.73 | Improved |
| introduce RCP by concatenation instead of gating (ablation) | PGFN · Rain200H | PSNR (dB): 30.73 -> 29.52 | Hurt |
| use FADformer instead of DRSformer | FADformer · SPA-Data | PSNR (dB): 48.54 -> 49.21 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining (ICML 2025 · similarity 0.89)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (AAAI 2024 · similarity 0.88)
- FMRNet: Image Deraining via Frequency Mutual Revision (AAAI 2024 · similarity 0.88)
- Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing (AAAI 2025 · similarity 0.87)
- Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining (CVPR 2025 · similarity 0.86)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (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.
