Research map / Image generation / Image restoration
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
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 pixel-wise dilation filtering (ablation) | EfDeRain · Rain100H | PSNR: 30.12 -> 30.27 | Helped |
| Add pixel-wise dilation filtering (ablation) | EfDeRain · Rain100H | SSIM: 0.8834 -> 0.8918 | Helped |
| Add pixel-wise dilation filtering (ablation) | EfDeRain · Rain100H | Time (ms): 4.41 -> 6.05 | Hurt |
| Add SSIM loss (ablation) | EfDeRain with dilation filtering · Rain100H | PSNR: 30.27 -> 30.35 | Helped |
| Add SSIM loss (ablation) | EfDeRain with dilation filtering · Rain100H | SSIM: 0.8918 -> 0.8970 | Helped |
| Add SSIM loss (ablation) | EfDeRain with dilation filtering · Rain100H | Time (ms): 6.05 -> 5.93 | Helped |
| Add RainMix augmentation (ablation) | EfDeRain with dilation filtering and L1 plus SSIM losses · Rain100H | PSNR: 30.35 -> 31.02 | Helped |
| Add RainMix augmentation (ablation) | EfDeRain with dilation filtering and L1 plus SSIM losses · Rain100H | SSIM: 0.8970 -> 0.9079 | Helped |
| Add RainMix augmentation (ablation) | EfDeRain with dilation filtering and L1 plus SSIM losses · Rain100H | Time (ms): 5.93 -> 5.97 | Hurt |
| Train with SSIM loss (ablation) | EfDeRain · Rain100H visual results | rain-streak removal and detail recovery | Mixed |
| Use RainMix augmentation (ablation) | EfDeRain · SPA | real-rain trace removal | Helped |
Closest papers by meaning
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.90)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (AAAI 2024 · similarity 0.88)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
- Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining (CVPR 2025 · similarity 0.87)
- Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning (AAAI 2025 · similarity 0.87)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 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.