AI Paper Atlas

Research map / Image generation / Image restoration

Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration

Chujie Qin, Ruiqi Wu, Zikun Liu, Xin Lin, Chun-Le Guo, Hyun Hee Park, Chongyi Li

ECCV 2024 · Image generation › Image restoration · approach: Priors for restoration networks · 12 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 MIM pre-training with 50% pixel masking and MAC fine-tuning to PromptIRPromptIR · All-in-one, average of 7 tasksPSNR: 28.17 -> 28.76Improved
add RAM pipeline to SwinIRSwinIR · All-in-one, average of 7 tasksPSNR: 26.64 -> 27.28Improved
add RAM to PromptIR on kernel deblurringPromptIR · LSDIR-BlurPSNR: 31.01 -> 29.57Hurt
add RAM to PromptIR on dehazing and low-light enhancementPromptIR · SOTS and LOLPSNR: SOTS 28.70 -> 29.64; LOL 21.19 -> 24.46Improved
increase masking ratio to 80% (ablation)RAM-SwinIR · All-in-one, average of 7 tasksPSNR: 27.28 -> 27.08Hurt
vary masking ratio between 20% and 60% (ablation)RAM-SwinIR · All-in-one, average of 7 tasksPSNR: 27.28 (20%), 27.21 (40%), 27.28 (50%), 27.26 (60%)No clear effect
pre-train MIM with paired degraded/clean data instead of ground truth only (ablation)RAM-SwinIR · All-in-one, average of 7 tasksPSNR: 26.62 -> 27.28Improved
select fine-tuning layers by MAC instead of IG or random (ablation)RAM-SwinIR · All-in-one, average of 7 tasksPSNR: 26.92 (IG) -> 27.28Improved
fine-tune 100% of layers instead of 10% (ablation)RAM-SwinIR · In-distribution averagePSNR: 27.28 -> 27.54Improved
fine-tune 100% of layers instead of 10% (ablation)RAM-SwinIR · Out-of-distribution denoising averagePSNR: 17.99 -> 15.93Hurt
use 1x1 mask patches instead of 4x4 or 8x8 (ablation)RAM-SwinIR pre-training · qualitative reconstructionreconstruction qualityImproved

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