Research map / Video / Video segmentation and tracking
Self-Aligned Video Deraining With Transmission-Depth Consistency
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 the full self-aligned deraining method with transmission-depth consistency | Video deraining · Synthetic rainy data | PSNR: 16.57 -> 17.52 | Helped |
| use the full self-aligned deraining method with transmission-depth consistency | Video deraining · Synthetic rainy data | SSIM: 0.7033 -> 0.7284 | Helped |
| add temporal consistency (ablation) | Video deraining method · Synthetic rainy data | PSNR: 14.56 -> 17.52 | Helped |
| add temporal consistency (ablation) | Video deraining method · Synthetic rainy data | SSIM: 0.5387 -> 0.7284 | Helped |
| add DepthNet (ablation) | Rain accumulation removal module · Synthetic rainy data | PSNR: 16.15 -> 17.52 | Helped |
| add DepthNet (ablation) | Rain accumulation removal module · Synthetic rainy data | SSIM: 0.6408 -> 0.7284 | Helped |
| train DepthNet rather than freezing it (ablation) | Rain accumulation removal module · Synthetic rainy data | PSNR: 16.43 -> 17.52 | Helped |
| train DepthNet rather than freezing it (ablation) | Rain accumulation removal module · Synthetic rainy data | SSIM: 0.6874 -> 0.7284 | Helped |
| add PoseNet-based camera-pose estimation (ablation) | Rain accumulation removal module · Synthetic rainy data | PSNR: 17.28 -> 17.52 | Helped |
| add PoseNet-based camera-pose estimation (ablation) | Rain accumulation removal module · Synthetic rainy data | SSIM: 0.7071 -> 0.7284 | Helped |
Closest papers by meaning
- Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence (CVPR 2020 · similarity 0.93)
- Frame-Consistent Recurrent Video Deraining With Dual-Level Flow (CVPR 2019 · similarity 0.91)
- Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining (CVPR 2025 · similarity 0.88)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
- NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction (AAAI 2024 · similarity 0.87)
- DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments (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.