Research map / Image generation / Image restoration
A Model-Driven Deep Neural Network for Single Image Rain Removal
Check 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 |
|---|---|---|---|
| Increase the number of RCDNet stages from S=0 to S=2 (ablation) | RCDNet · Rain100L | PSNR: 35.93 -> 38.46 | Helped |
| Increase the number of RCDNet stages from S=0 to S=2 (ablation) | RCDNet · Rain100L | SSIM: 0.9689 -> 0.9813 | Helped |
| Increase stages from S=2 to S=17 (ablation) | RCDNet · Rain100L | PSNR: 38.46 -> 40.00 | Helped |
| Increase stages from S=2 to S=17 (ablation) | RCDNet · Rain100L | SSIM: 0.9813 -> 0.9860 | Helped |
| Increase stages from S=17 to S=20 (ablation) | RCDNet · Rain100L | PSNR: 40.00 -> 39.91 | Hurt |
| Increase stages from S=17 to S=20 (ablation) | RCDNet · Rain100L | SSIM: 0.9860 -> 0.9858 | Hurt |
| Use the RCDNet architecture instead of JORDER_E | Single-image deraining · Rain100L | PSNR: 38.59 -> 40.00 | Helped |
| Use the RCDNet architecture instead of JORDER_E | Single-image deraining · Rain100H | PSNR: 30.50 -> 31.28 | Helped |
| Use the RCDNet architecture instead of PReNet | Single-image deraining · Rain100H | SSIM: 0.9053 -> 0.9093 | Helped |
| Use the RCDNet architecture instead of PReNet | Single-image deraining · Rain1400 | PSNR: 32.55 -> 33.04 | Helped |
| Use the RCDNet architecture instead of PReNet | Single-image deraining · Rain1400 | SSIM: 0.9459 -> 0.9472 | Helped |
| Use the RCDNet architecture instead of JORDER_E | Single-image deraining · Rain12 | PSNR: 36.69 -> 37.71 | Helped |
Closest papers by meaning
- Removing Rain From Single Images via a Deep Detail Network (CVPR 2017 · similarity 0.93)
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.93)
- Rain Streak Removal via Dual Graph Convolutional Network (AAAI 2021 · similarity 0.92)
- Semi-Supervised Transfer Learning for Image Rain Removal (CVPR 2019 · similarity 0.91)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.89)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.88)
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.