AI Paper Atlas

Research map / Image generation / Image restoration

Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration

Shihao Zhou, Jinshan Pan, Jinglei Shi, Duosheng Chen, Lishen Qu, Jufeng Yang

ECCV 2024 · Image generation › Image restoration · approach: Priors for restoration networks · 32 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
replace multiple dynamic convolution with gated dynamic decoupler (GDD) (ablation)FPro · SPADPSNR: 48.52 -> 48.91Improved
share a single GDD across the DPBs (ablation)FPro · SPADPSNR: 48.91 -> 48.99Improved
add high-frequency prompt modulator (HPM) (ablation)FPro · SPADPSNR: 48.77 -> 48.99Improved
add low-frequency prompt modulator (LPM) (ablation)FPro · SPADPSNR: 48.89 -> 48.99Improved
frequency prompts instead of spatial prompts (FPro vs PromptIR)prompt-based restoration · Rain100LPSNR: 37.04 -> 39.20Improved
frequency prompts vs PromptRestorer (which used extra training data)prompt-based restoration · Rain100LPSNR: 39.04 -> 39.20Improved
FPro vs DRSformerreal rain removal · SPADPSNR: 48.53 -> 48.99Improved
FPro vs best SSIM baselinesFPro · SPAD SSIM / TIP-2018 SSIMSSIM: 0.9936 vs 0.9941 (SCD-Former); 0.879 vs 0.894 (Wang et al.)Mixed
FPro vs DRSformer on computeFPro · SPAD efficiencyFLOPs/G: 242.9 -> 81.9Improved
FPro vs prior methods on NIQEFPro · real rainy imagesNIQE: 5.5942 -> 5.2999Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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