AI Paper Atlas

Research map / Image generation / Image restoration

Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank

Chenxu Wang, Kai Zhang, Jian Yang

CVPR 2026 · Image generation › Image restoration · approach: Efficient restoration architectures

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
set degradation bank size M to 64 rather than 24, 32 or 128 (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 32.30 / 32.41 / 32.34 -> 32.53Mixed
add FFT frequency loss to pixel loss (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 31.88 -> 32.23Improved
add degradation classification loss L_deg (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 32.23 -> 32.29Improved
add matching classification loss L_match (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 32.29 -> 32.53Improved
build degradation bank from clean HQ and residual instead of Gaussian-noised HQ (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 31.99 -> 32.53Improved
build degradation bank from clean HQ and residual instead of LQ only (ablation)R2R · All-in-one 3 degradations (average)PSNR (dB): 32.33 -> 32.53No clear effect
replace PromptIR-style internal modulation with retrieval-based degradation bankR2R · All-in-one 3 degradations (average)PSNR (dB) / MACs: 32.06 -> 32.53 PSNR; 132G -> 12G MACsImproved
scale from single-task to three-task trainingR2R · single vs three-task restorationPSNR (dB)Improved
R2R versus PromptIR on single-task denoisingR2R · CBSD68 sigma=15 (single task)PSNR (dB): 34.34 -> 34.27Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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