Research map / Video / Video segmentation and tracking
Semi-Supervised Video Deraining With Dynamical Rain Generator
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 S2VD instead of SLDNet | Video deraining · NTURain synthetic test | PSNR: 34.89 -> 37.37 | Helped |
| Add the likelihood term to MSE training (ablation) | S2VD derainer, labeled data · NTURain synthetic test | PSNR: 36.11 -> 37.12; 1.01dB PSNR | Helped |
| Add the likelihood term to MSE training (ablation) | S2VD derainer, labeled data · NTURain synthetic test | SSIM: 0.9602 -> 0.9673; 0.0071 SSIM | Helped |
| Add the MRF regularizer (ablation) | S2VD trained on labeled data · NTURain synthetic test | PSNR: 37.12 -> 37.96 | Helped |
| Add unlabeled real videos during training (ablation) | S2VD · Real rainy videos | deraining quality | Helped |
| Add unlabeled real videos during training (ablation) | S2VD · NTURain synthetic test | PSNR: 37.96 -> 37.37 | Hurt |
| Increase MRF weight rho from 0 to 0.1 (ablation) | S2VD · NTURain synthetic test | PSNR: 38.18 -> 38.05 | Hurt |
| Increase MRF weight rho from 0.1 to 0.5 (ablation) | S2VD · NTURain synthetic test | PSNR: 38.05 -> 37.37 | Hurt |
| Increase MRF weight rho from 0.5 to 1 (ablation) | S2VD · NTURain synthetic test | PSNR: 37.37 -> 35.50 | Hurt |
| Increase MRF weight rho from 1 to 2 (ablation) | S2VD · NTURain synthetic test | PSNR: 35.50 -> 31.55 | Hurt |
Closest papers by meaning
- Memory Oriented Transfer Learning for Semi-Supervised Image Deraining (CVPR 2021 · similarity 0.90)
- Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining (CVPR 2025 · similarity 0.90)
- NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction (AAAI 2024 · similarity 0.87)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.87)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.87)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.85)
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.