Research map / Image generation / Image restoration
Rain Streak Removal Using Layer Priors
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 |
|---|---|---|---|
| Use background and rain layer GMM patch priors instead of the TV model without GMM priors (ablation) | Rain Streak Removal Using Layer Priors · Synthetic example | SSIM: 0.7777 -> 0.9243 (background, 5 iterations); 0.7116 -> 0.8309 (rain, 5 iterations) | Helped |
| Increase optimization iterations from 5 to 20 (ablation) | Rain Streak Removal Using Layer Priors · Synthetic example | SSIM: 0.9243 -> 0.9290 (background); 0.8309 -> 0.8791 (rain) | Helped |
| Use GMM patch priors rather than no GMM priors | Rain Streak Removal Using Layer Priors · Synthetic rain-removal datasets | SSIM | Helped |
Closest papers by meaning
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.91)
- Video Rain Streak Removal by Multiscale Convolutional Sparse Coding (CVPR 2018 · similarity 0.91)
- Removing Raindrops and Rain Streaks in One Go (CVPR 2021 · similarity 0.90)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.87)
- Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning (AAAI 2025 · similarity 0.87)
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.