Research map / Image generation / Image restoration
Detail-recovery Image Deraining via Context Aggregation Networks
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 |
|---|---|---|---|
| Add SE to the rain-residual baseline (ablation) | DRD-Net · Rain200L | PSNR: 35.57 -> 36.17 | Helped |
| Add SE to the rain-residual baseline (ablation) | DRD-Net · Rain200H | PSNR: 26.20 -> 26.49 | Helped |
| Add SE to the rain-residual baseline (ablation) | DRD-Net · Rain800 | PSNR: 25.83 -> 26.04 | Helped |
| Add the detail-repair network with direct blocks (ablation) | DRD-Net · Rain200L | PSNR: 36.17 -> 36.89 | Helped |
| Add the detail-repair network with direct blocks (ablation) | DRD-Net · Rain200H | PSNR: 26.49 -> 27.16 | Helped |
| Add the detail-repair network with direct blocks (ablation) | DRD-Net · Rain800 | PSNR: 26.04 -> 26.09 | Helped |
| Use SDCAB instead of direct blocks for detail repair (ablation) | DRD-Net · Rain200L | PSNR: 36.89 -> 37.15 | Helped |
| Use SDCAB instead of direct blocks for detail repair (ablation) | DRD-Net · Rain200H | PSNR: 27.16 -> 28.16 | Helped |
| Use SDCAB instead of direct blocks for detail repair (ablation) | DRD-Net · Rain800 | PSNR: 26.09 -> 26.32 | Helped |
| Increase feature maps from M=16 to M=64 at D=16+3 (ablation) | DRD-Net · Rain200H | PSNR: 26.93 -> 28.16 | Helped |
| Increase depth from D=8+3 to D=16+3 at M=64 (ablation) | DRD-Net · Rain200H | PSNR: 26.97 -> 28.16 | Helped |
| Use DRD-Net rather than the strongest reported baseline | Image deraining methods · Rain200H | PSNR: 26.60 -> 28.16 | Helped |
Closest papers by meaning
- Multi-Decoding Deraining Network and Quasi-Sparsity Based Training (CVPR 2021 · similarity 0.87)
- UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization (CVPR 2026 · similarity 0.87)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.85)
- FMRNet: Image Deraining via Frequency Mutual Revision (AAAI 2024 · similarity 0.85)
- Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning (AAAI 2025 · similarity 0.84)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.84)
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.