Research map / Image generation / Image restoration
Learning Rain Location Prior for Nighttime Deraining
Fan Zhang, Shaodi You, Yu Li, Ying Fu
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 Rain Location Prior (RLP) to the deraining module (ablation) | U-Net · GTAV-NightRain | PSNR (dB): 36.63 -> 37.08 | Improved |
| add RLP to the deraining module (ablation) | Uformer-T · GTAV-NightRain | PSNR (dB): 37.45 -> 37.95 | Improved |
| add RPIM on top of RLP (ablation) | Uformer-T · GTAV-NightRain | PSNR (dB): 37.95 -> 38.44 | Improved |
| add RPIM on top of RLP (ablation) | PReNet · GTAV-NightRain | PSNR (dB): 35.00 -> 34.31 | Hurt |
| add RLP and RPIM (ablation) | MPRNet · GTAV-NightRain | PSNR (dB): 35.21 -> 35.67 | Improved |
| add RLP and RPIM to larger model (ablation) | Uformer-B · GTAV-NightRain | PSNR (dB): 39.41 -> 39.77 | Improved |
| add RLP and RPIM to daytime deraining | U-Net · Rain13k (avg of 5 test sets) | PSNR (dB): 28.39 -> 29.10 | Improved |
| add RLP and RPIM to daytime deraining | Uformer · Rain13k (avg of 5 test sets) | PSNR (dB): 30.50 -> 30.74 | Improved |
| add RPIM on top of RLP (ablation) | Uformer · Rain13k Test1200 | PSNR (dB): 31.86 -> 31.67 | Hurt |
| supervise RLP output with thresholded rain streak masks (ablation) | RLP · GTAV-NightRain | PSNR | No clear effect |
Closest papers by meaning
- Learning Rain Location Prior for Nighttime Deraining and Beyond (TPAMI 2025 · similarity 0.97)
- Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (CVPR 2019 · similarity 0.91)
- NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction (AAAI 2024 · similarity 0.90)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.89)
- Rethinking Nighttime Image Deraining via Learnable Color Space Transformation (NeurIPS 2025 · similarity 0.89)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · 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.
