AI Paper Atlas

Research map / Image generation / Image restoration

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

Cong Wang, Jinshan Pan, Wei Wang, Jiangxin Dong, Mengzhu Wang, Yakun Ju, Junyang Chen

NeurIPS 2023 · Image generation › Image restoration · approach: Priors for restoration networks · 11 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
prompt with raw pre-trained degradation features (vs no conditional branch) (ablation)PromptRestorer · GoPro ablationPSNR: 30.138 -> 31.015Improved
prompt with raw pre-trained degradation features (vs learnable conditional branch) (ablation)PromptRestorer · GoPro ablationPSNR: 30.646 -> 31.015Improved
add local prompting perceptor L2P (ablation)PromptRestorer · GoPro ablationPSNR: 30.819 -> 31.015Improved
add global prompting perceptor G2P (ablation)PromptRestorer · GoPro ablationPSNR: 30.697 -> 31.015Improved
add gated degradation perception propagation (ablation)PromptRestorer · GoPro ablationPSNR: 30.924 -> 31.015Improved
add Q-InAtt in G2P (ablation)PromptRestorer · GoPro ablationPSNR: 30.914 -> 31.015Improved
add KV-InAtt in G2P (ablation)PromptRestorer · GoPro ablationPSNR: 30.906 -> 31.015Improved
PromptRestorer vs Restormer on deraining averageRestormer · Deraining averagePSNR: 33.96 -> 34.05Improved
PromptRestorer vs Restormer on dehazing SOTS-Indoor (MAXIM best prior)MAXIM · SOTS-IndoorPSNR: 38.11 -> 42.54Improved
PromptRestorer vs Restormer on CSD desnowingRestormer · CSDPSNR: 35.43 -> 37.48Improved
PromptRestorer vs Restormer on real-world RealBlur-JRestormer · RealBlur-JPSNR: 28.96 -> 28.82Hurt
PromptRestorer vs DeHamer on Dense-HazeDeHamer · Dense-HazePSNR: 16.62 -> 15.86Hurt

Later papers that compared with this method

2 later accepted papers report PromptRestorer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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