AI Paper Atlas

Research map / Image generation / Image restoration

Boosting Filter Optimization and Prompt-Guided Decoding for Mixed Degradation Image Restoration

Yubin Gu, Yuan Meng, Xiaoshuai Sun, Jiayi Ji, Rongrong Ji

IJCV 2026 · Image generation › Image restoration · approach: Efficient restoration architectures · 5 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 LDO module to the baseline (ablation)MDIR baseline · CIR averagePSNR: 31.030 -> 32.937Improved
add CFE module on top of baseline + LDO (ablation)MDIR · CIR averagePSNR: 32.937 -> 33.213Improved
add CFE to IRNeXt (ablation)IRNeXt · CIR averagePSNR: 32.568 -> 32.823Improved
add CFE to Restormer (ablation)Restormer · CIR averagePSNR: 31.621 -> 31.813Improved
unified training over all degradations vs one-to-one training on noise (ablation)MDIR · CIR noisePSNR: 35.499 -> 35.736 when trained separatelyHurt
unified training vs one-to-one training on haze (ablation)MDIR · CIR hazePSNR: 30.056 -> 31.687Improved
unified training vs one-to-one training on rain+haze+noise (ablation)MDIR · CIR rain+haze+noisePSNR: 27.619 -> 28.458Improved
unified training vs one-to-one training on snow (ablation)MDIR · CIR snowPSNR: 34.811 -> 35.583 when trained separatelyHurt
increase LDO kernel size from 3 to 7 (ablation)MDIR · Rain100HPSNR: 33.086 -> 33.664Improved
increase LDO kernel size from 3 to 7 (ablation)MDIR · Rain100LPSNR: 39.090 -> 38.933Hurt
MDIR vs PromptIR on CIRMDIR · CIR averagePSNR: 32.133 -> 33.213Improved
MDIR vs second-best on derainingMDIR · Rain100HPSNR: 31.770 -> 33.086Improved

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