Research map / Image generation / Image restoration
MetaWeather: Few-Shot Weather-Degraded Image Restoration
Youngrae Kim, Younggeol Cho, Thanh-Tung Nguyen, Seunghoon Hong, Dongman Lee
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 |
|---|---|---|---|
| match degradation patterns instead of backgrounds between query and support (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 22.11 -> 24.28 | Improved |
| add channel matching to spatial matching (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 23.05 -> 24.28 | Improved |
| use channel matching only versus spatial matching only (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 23.05 -> 23.90 | Improved |
| add spatial matching alone over no matching (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 22.82 -> 23.05 | No clear effect |
| increase support set from 1 to 4 pairs (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 24.28 -> 24.95 | Improved |
| increase support set from 1 to 4 pairs (ablation) | WeatherDiffusion · BID Task II.A | PSNR (dB) average: 22.27 -> 22.25 | No clear effect |
| fine-tune only bias parameters at meta-test rather than all parameters (ablation) | MetaWeather · BID Task II.A | PSNR (dB) average: 22.19 -> 24.28 | Improved |
| fine-tune only bias parameters for baselines (ablation) | FocalNet · BID Task II.A | PSNR (dB) average: 21.53 -> 20.62 | Hurt |
| different random support set selections (ablation) | MetaWeather · BID Task II.A | PSNR (dB): mean 24.16, std 0.20 | No clear effect |
| add degradation pattern matching and channel matching to Visual Token Matching (ablation) | VTM · SPA-Data | PSNR (dB): 32.27 -> 34.81 | Improved |
| adapt with few-shot support rather than using real-world pretrained restoration model | Patil et al. · SPA-Data | PSNR (dB): 20.26 -> 34.81 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (AAAI 2025 · similarity 0.89)
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start (NeurIPS 2025 · similarity 0.88)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.88)
- Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration (AAAI 2025 · similarity 0.87)
- Language-driven All-in-one Adverse Weather Removal (CVPR 2024 · similarity 0.86)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.86)
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.
