Research map / Graph learning / Knowledge and temporal graphs
Rain Streak Removal via Dual Graph Convolutional Network
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 |
|---|---|---|---|
| Use dual spatial and channel GCNs instead of the baseline without GCNs (ablation) | Dual GCN · Rain200H | PSNR: 29.13 -> 31.15 | Helped |
| Add channel GCN to the baseline (ablation) | Rain-removal network · Rain200H | PSNR: 29.13 -> 30.53 | Helped |
| Add spatial GCN to the baseline (ablation) | Rain-removal network · Rain200H | PSNR: 29.13 -> 30.61 | Helped |
| Increase kernel count and unit count (ablation) | Dual GCN · Rain200H | PSNR: 29.17 -> 31.37 | Helped |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · Rain12 | PSNR: 37.86 -> 38.99 | Helped |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · Rain200L | PSNR: 39.17 -> 40.73 | Helped |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · Rain200H | PSNR: 30.24 -> 31.15 | Helped |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · DID-Data | PSNR: 34.68 -> 34.37 | Hurt |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · DDN-Data | PSNR: 33.05 -> 33.01 | Hurt |
| Use the full Dual GCN method rather than the strongest listed baseline | Rain-removal methods · SPA-Data | PSNR: 43.36 -> 44.18 | Helped |
Closest papers by meaning
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.93)
- Removing Rain From Single Images via a Deep Detail Network (CVPR 2017 · similarity 0.93)
- A Model-Driven Deep Neural Network for Single Image Rain Removal (CVPR 2020 · similarity 0.92)
- 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 0.89)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 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.