Research map / Architectures and efficiency / Neural architecture search
Removing Raindrops and Rain Streaks in One Go
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 |
|---|---|---|---|
| search RSR and RDR block architectures instead of selecting operations randomly (ablation) | CCN · RainDS-Syn RS | PSNR: 30.72 -> 35.12 | Helped |
| search RSR and RDR block architectures instead of selecting operations randomly (ablation) | CCN · RainDS-Syn RD | PSNR: 29.43 -> 33.89 | Helped |
| search RSR and RDR block architectures instead of selecting operations randomly (ablation) | CCN · RainDS-Syn RDS | PSNR: 28.17 -> 32.27 | Helped |
| use complementary cascaded RSR/RDR blocks rather than RSR-only blocks (ablation) | CCN · RainDS-Syn RDS | PSNR: 30.07 -> 32.27 | Helped |
| use complementary cascaded RSR/RDR blocks rather than RDR-only blocks (ablation) | CCN · RainDS-Syn RDS | PSNR: 29.39 -> 32.27 | Helped |
| change the NAS initialization across four search runs (ablation) | CCN · RainDS-Syn RDS | PSNR: 32.47; 32.27; 31.79; 32.53 | No clear effect |
| use CCN rather than the strongest reported baseline | CCN · RainDS real RDS | PSNR: 21.20 -> 23.09 | Helped |
| use CCN rather than the strongest reported baseline | CCN · Rain200H | PSNR: 28.16 -> 29.12 | Helped |
Closest papers by meaning
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.93)
- Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (CVPR 2019 · similarity 0.92)
- Multi-Scale Progressive Fusion Network for Single Image Deraining (CVPR 2020 · similarity 0.91)
- Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence (CVPR 2020 · similarity 0.91)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.89)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.89)
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.