Research map / Image generation / Image restoration
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
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 |
|---|---|---|---|
| Train SPANet on the proposed real-rain dataset | SPANet · Proposed real-rain test set | PSNR | Helped |
| Train existing CNN derainers on the proposed real-rain dataset instead of synthetic data | CNN-based derainers · Proposed real-rain test set | PSNR | Helped |
| Use spatial attention to identify and remove rain regions | SPANet · DID-MDN test set | PSNR: 27.95 -> 30.05 | Helped |
| Add a self-attention branch to the SAM (ablation) | SPANet · Proposed real-rain test set | PSNR: 37.70 -> 38.06 | Helped |
| Add explicit attention-loss supervision (ablation) | SPANet · Proposed real-rain test set | PSNR: 37.39 -> 38.06 | Helped |
| Use four SAMs with shared weights rather than four unshared SAMs (ablation) | SPANet · Proposed real-rain test set | PSNR: 37.47 -> 38.06 | Helped |
| Use one SAM four times instead of the basic Resnet-like network (ablation) | SPANet · Proposed real-rain test set | PSNR: 37.43 -> 37.43 | No clear effect |
| Use four unshared SAMs instead of the basic Resnet-like network (ablation) | SPANet · Proposed real-rain test set | PSNR: 37.43 -> 37.47 | Helped |
Closest papers by meaning
- Removing Raindrops and Rain Streaks in One Go (CVPR 2021 · similarity 0.92)
- Multi-Scale Progressive Fusion Network for Single Image Deraining (CVPR 2020 · similarity 0.92)
- Rain Streak Removal via Dual Graph Convolutional Network (AAAI 2021 · similarity 0.91)
- Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework (CVPR 2018 · similarity 0.91)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.91)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.90)
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.