Research map / Image generation / Image restoration
Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add squeeze-and-excitation blocks to CAN (SCAN vs CAN) (ablation) | SCAN · Rain800 | PSNR: 22.45 -> 23.45 | Improved |
| add squeeze-and-excitation blocks to CAN (SCAN vs CAN) (ablation) | SCAN · Rain100H | PSNR: 22.93 -> 23.56 | Improved |
| remove batch normalization from SCAN (ablation) | SCAN · Rain800 | PSNR: 23.11 -> 23.45 | Improved |
| remove batch normalization from SCAN (ablation) | SCAN · Rain100H | PSNR: 23.09 -> 23.56 | Improved |
| use exponentially increasing dilation instead of plain dilation 1 (ablation) | SCAN/CAN · Rain800 | PSNR: 22.10 -> 22.45 | Improved |
| use exponentially increasing dilation instead of plain dilation 1 (ablation) | SCAN/CAN · Rain100H | PSNR: 21.46 -> 22.93 | Improved |
| add recurrent stages with ConvGRU full prediction on top of SCAN (ablation) | RESCAN · Rain800 | PSNR: 23.45 -> 24.09 | Improved |
| add recurrent stages with ConvGRU full prediction on top of SCAN (ablation) | RESCAN · Rain100H | PSNR: 23.56 -> 26.45 | Improved |
| keep previous-stage states (recurrent) instead of iterative framework without states (ablation) | SCAN · Rain100H | PSNR: 22.81 -> 26.45 | Improved |
| use full prediction instead of additive prediction (ConvGRU) (ablation) | RESCAN · Rain100H | PSNR: 24.00 -> 26.45 | Improved |
| use full prediction instead of additive prediction (ConvGRU) (ablation) | RESCAN · Rain800 | PSNR: 23.31 -> 24.18 | Improved |
| use ConvGRU instead of ConvRNN with full prediction (ablation) | RESCAN · Rain100H | PSNR: 23.44 -> 26.45 | Improved |
Closest papers by meaning
- Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (TPAMI 2019 · similarity 0.94)
- 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 0.93)
- Rain Streak Removal via Dual Graph Convolutional Network (AAAI 2021 · similarity 0.93)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · 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.
