Research map / Image generation / Image restoration
Controlling the Rain: From Removal to Rendering
Siqi Ni, Xueyun Cao, Tao Yue, Xuemei Hu
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 |
|---|---|---|---|
| Use RICNet for deraining | RainLevel5 · RainLevel5 | PSNR: 35.99 -> 37.81 | Improved |
| Use RICNet for deraining | Rain12000 · Rain12000 | PSNR: 32.39 -> 32.67 | Improved |
| Use RICNet for deraining | Rain800 · Rain800 | PSNR: 27.50 -> 27.11 | Hurt |
| Use RICNet for deraining | Rain200H · Rain200H | PSNR: 28.82 -> 28.84 | Improved |
| Use RICNet for deraining | SPAData · SPAData | PSNR: 41.47 -> 37.98 | Hurt |
| Remove NBM (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 5.132 | Hurt |
| Use only high-level interpolation (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 4.974 | Hurt |
| Use only low-level interpolation (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 4.955 | Hurt |
| Remove HOG loss (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 5.612 | Hurt |
| Remove autocorrelation loss (ablation) | RICNet rain rendering · Rain rendering | FSIM: 0.850 -> 0.802 | Hurt |
| Use random rather than decremental training (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 4.975 | Hurt |
| Use incremental rather than decremental training (ablation) | RICNet rain rendering · Rain rendering | NIQE: 3.985 -> 5.031 | Hurt |
Closest papers by meaning
- Removing Raindrops and Rain Streaks in One Go (CVPR 2021 · similarity 0.90)
- Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (CVPR 2019 · similarity 0.89)
- Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (TPAMI 2019 · similarity 0.89)
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.89)
- Removing Rain From Single Images via a Deep Detail Network (CVPR 2017 · similarity 0.88)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · 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.
