AI Paper Atlas

Research map / Image generation / Image restoration

Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration

Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie

TPAMI 2025 · Image generation › Image restoration · approach: Efficient restoration architectures · 13 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
add CPL (SPM + CPR) to PromptIRPromptIR · Three-task AiOIRPSNR (dB): 32.06 -> 32.78Improved
add CPL to PromptIRPromptIR · Five-task AiOIRPSNR (dB): 29.15 -> 30.55Improved
add CPL to PromptIRPromptIR · Seven-task AiOIRPSNR (dB): improving upon the PromptIR baseline by 1.42 dBImproved
add CPL to PromptIRPromptIR · WeatherBench real-worldPSNR (dB): 27.86 -> 30.35Improved
add CPL to PromptIRPromptIR · CDD-11 compositePSNR (dB): 25.90 -> 29.07Improved
add CPR on top of SPM (k=1) (ablation)SPM · Three-task AiOIRPSNR (dB): 32.48 -> 32.78Improved
increase top-k from 1 to 2 in SPM (no CPR) (ablation)SPM · Three-task AiOIRPSNR (dB): 32.48 -> 32.54Improved
increase top-k from 1 to 3 in SPM (ablation)SPM · Three-task AiOIRPSNR (dB): 32.54 -> 32.23Hurt
increase top-k from 1 to 2 in SPM (ablation)SPM · Five-task AiOIRPSNR (dB): 30.06 -> 29.68Hurt
increase top-k from 1 to 3 in SPM (ablation)SPM · Five-task AiOIRPSNR (dB): 30.06 -> 29.54Hurt
increase number of prompts from 5 to 15 in dense PromptIR (ablation)PromptIR · CDD-11 compositePSNR (dB): 25.90 -> 26.10No clear effect
increase number of prompts from 5 to 15 with CPL (ablation)PromptIR+CPL · CDD-11 compositePSNR (dB): 29.07 -> 29.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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