Research map / Image generation / Image restoration
Single Image Deraining: A Comprehensive Benchmark Analysis
Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao
Check 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 |
|---|---|---|---|
| Use a rain-streak-specific derainer rather than the degraded input | Synthetic rain-streak images · Rain streak (S) | PSNR: 25.95 -> 29.39 | Improved |
| Use DeRaindrop, specialized for raindrops, rather than the degraded input | Synthetic raindrop images · Raindrop (S) | PSNR: 25.40 -> 31.57 | Improved |
| Apply deraining before detection | YOLO-V3 on RID · RID | mAP: 27.84 -> 23.75 | Hurt |
| Apply deraining before detection | YOLO-V3 on RIS · RIS | mAP: 23.27 -> 18.71 | Hurt |
| Use a rain-streak detection-and-removal strategy | Synthetic rain-streak deraining · Rain streak (S) | PSNR | Improved |
| Use rain-focused attention or masks to guide removal | Rain-streak and raindrop deraining · Rain streak (S), Raindrop (S) | PSNR | Improved |
| Use a model with fewer physical priors and rain-type assumptions | CGAN · Rain and mist (R) | NIQE | Improved |
| Use patch-based GMM rather than DeRaindrop | Human-rated raindrop removal · Raindrops (R), subjective survey | subjective score: 0.80 -> 1.14 | Improved |
| Use GAN-based CGAN rather than other tested derainers | Human-rated rain-streak removal · Rain streak (R), subjective survey | subjective score: 1.15 -> 1.26 | Improved |
| Use DID-MDN rather than CGAN | Human-rated rain-and-mist removal · Rain and mist (R), subjective survey | subjective score: 1.22 -> 1.40 | Improved |
| Use deraining as a preprocessing step for object detection | Existing derainers on RID and RIS · RID and RIS | mAP | Hurt |
| Use no-reference IQA metrics as a substitute for human judgments | Deraining evaluation · Real-world rainy images | subjective quality alignment | Hurt |
Closest papers by meaning
- Single Image Deraining: From Model-Based to Data-Driven and Beyond (TPAMI 2020 · similarity 0.94)
- EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining (AAAI 2021 · similarity 0.92)
- Not Just Streaks: Towards Ground Truth for Single Image Deraining (ECCV 2022 · similarity 0.92)
- UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization (CVPR 2026 · similarity 0.92)
- From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal (ICCV 2023 · similarity 0.91)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · 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.
