AI Paper Atlas

Research map / Image generation / Image restoration

MetaWeather: Few-Shot Weather-Degraded Image Restoration

Youngrae Kim, Younggeol Cho, Thanh-Tung Nguyen, Seunghoon Hong, Dongman Lee

ECCV 2024 · Image generation › Image restoration · approach: Efficient restoration architectures · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
match degradation patterns instead of backgrounds between query and support (ablation)MetaWeather · BID Task II.APSNR (dB) average: 22.11 -> 24.28Improved
add channel matching to spatial matching (ablation)MetaWeather · BID Task II.APSNR (dB) average: 23.05 -> 24.28Improved
use channel matching only versus spatial matching only (ablation)MetaWeather · BID Task II.APSNR (dB) average: 23.05 -> 23.90Improved
add spatial matching alone over no matching (ablation)MetaWeather · BID Task II.APSNR (dB) average: 22.82 -> 23.05No clear effect
increase support set from 1 to 4 pairs (ablation)MetaWeather · BID Task II.APSNR (dB) average: 24.28 -> 24.95Improved
increase support set from 1 to 4 pairs (ablation)WeatherDiffusion · BID Task II.APSNR (dB) average: 22.27 -> 22.25No clear effect
fine-tune only bias parameters at meta-test rather than all parameters (ablation)MetaWeather · BID Task II.APSNR (dB) average: 22.19 -> 24.28Improved
fine-tune only bias parameters for baselines (ablation)FocalNet · BID Task II.APSNR (dB) average: 21.53 -> 20.62Hurt
different random support set selections (ablation)MetaWeather · BID Task II.APSNR (dB): mean 24.16, std 0.20No clear effect
add degradation pattern matching and channel matching to Visual Token Matching (ablation)VTM · SPA-DataPSNR (dB): 32.27 -> 34.81Improved
adapt with few-shot support rather than using real-world pretrained restoration modelPatil et al. · SPA-DataPSNR (dB): 20.26 -> 34.81Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy