AI Paper Atlas

Research map / Image generation / Image restoration

Ingredient-Oriented Multi-Degradation Learning for Image Restoration

Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao

CVPR 2023 · Image generation › Image restoration · approach: Efficient restoration architectures · 99 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
Use ingredient-oriented degradation reformulation with task-specific prior collection followed by learnable PCA integrationRestormer-based IDR · Rain100L, SOTS, BSD68, GoPro, and LOLPSNR: Rain100L: 35.63 vs 38.16; SOTS: 25.24 vs 25.23; BSD68: 31.60 vs 31.49; GoPro: 27.87 vs 26.87; LOL: 21.34 vs 21.87Mixed
Use IDR without fine-tuning on an unknown downstream taskIDR · TOLED and POLED UDC restorationPSNR: TOLED: 27.91 vs 26.89; POLED: 16.71 vs 13.92Improved
Include task-oriented prior learning before ingredient-oriented integration (ablation)IDR · Combined five-task image restoration datasetPSNRImproved
Use learnable PCA instead of random integration (ablation)IDR · Combined five-task image restoration datasetPSNRImproved
Use dynamic routing (ablation)IDR · Combined five-task image restoration datasetPSNRImproved
Use supervised degradation attention (ablation)IDR · Combined five-task image restoration datasetPSNRImproved
Train with five restoration tasks rather than the R+H+N subset (ablation)IDR · LOLPSNR: 7.82 -> 21.34Improved
Train with five restoration tasks rather than the R+H+N+B subset (ablation)IDR · GoProPSNR: 27.08 -> 27.87Improved
Train with five restoration tasks rather than the R+H+N+L subset (ablation)IDR · GoProPSNR: 25.50 -> 27.87Improved

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