Research map / Image generation / Image restoration
Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions
Read the paperCheck 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 |
|---|---|---|---|
| Add adaptively selected weather-specific parameters after learning shared weather-general features (ablation) | Ours · Outdoor-Rain | PSNR: 25.04 -> 25.31 | Helped |
| Add adaptively selected weather-specific parameters after learning shared weather-general features (ablation) | Ours · RainDrop | PSNR: 30.88 -> 31.31 | Helped |
| Add adaptively selected weather-specific parameters after learning shared weather-general features (ablation) | Ours · SnowTest100k-L | PSNR: 29.13 -> 29.71 | Helped |
| Replace adaptive expansion positions with random positions (ablation) | Ours · Outdoor-Rain | PSNR: 25.31 -> 25.14 | Hurt |
| Replace adaptive expansion positions with random positions (ablation) | Ours · RainDrop | PSNR: 31.31 -> 30.96 | Hurt |
| Replace adaptive expansion positions with random positions (ablation) | Ours · SnowTest100k-L | PSNR: 29.71 -> 29.28 | Hurt |
| Increase general-model parameter count rather than add learned weather-specific parameters (ablation) | Ours · Outdoor-Rain | PSNR: 25.31 -> 25.22 | Hurt |
| Increase general-model parameter count rather than add learned weather-specific parameters (ablation) | Ours · RainDrop | PSNR: 31.31 -> 30.99 | Hurt |
| Use 3×3 rather than 1×1 weather-specific convolutions (ablation) | Ours · Rain1400 | PSNR: 32.49 -> 32.75 | Helped |
| Use 3×3 rather than 1×1 weather-specific convolutions (ablation) | Ours · RESIDE | PSNR: 30.85 -> 30.90 | Helped |
| Add depth consistency loss (ablation) | Stage 1 · Outdoor-Rain | PSNR: 24.96 -> 25.04 | Helped |
| Add depth consistency loss (ablation) | Stage 1 · RainDrop | PSNR: 30.79 -> 30.88 | Helped |
Closest papers by meaning
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start (NeurIPS 2025 · similarity 0.90)
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (AAAI 2025 · similarity 0.89)
- Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration (AAAI 2025 · similarity 0.89)
- Language-driven All-in-one Adverse Weather Removal (CVPR 2024 · similarity 0.89)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.88)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · 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.