AI Paper Atlas

Research map / Image generation / Image restoration

Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration

Fengyang Xiao, Peng Hu, Lei Xu, XingE Guo, Guanyi Qin, Yuqi Shen, Chengyu Fang, Rihan Zhang, Chunming He, Sina Farsiu

CVPR 2026 · Image generation › Image restoration · approach: Efficient restoration architectures · 1 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 NR-IQA score as condition to the code-prediction Transformer (ablation)codebook restoration · WebPhoto-TestTOPIQ-G: 0.757 -> 0.790Improved
add dual codebook (common + HQ+) (ablation)score-conditioned model · WebPhoto-TestTOPIQ-G: 0.790 -> 0.806Improved
add NR-IQA quality optimization loss (ablation)score-conditioned dual-codebook model · WebPhoto-TestTOPIQ-G: 0.806 -> 0.822Improved
add dual codebook (ablation)score-conditioned model · WebPhoto-TestMusiq-K: 75.95 -> 76.04No clear effect
add all three components (score condition, dual codebook, quality optimization) (ablation)codebook restoration · WebPhoto-TestQ-Align: 3.78 -> 4.23Improved
add all components, inference cost (ablation)codebook restoration · WebPhoto-TestInference time (ms): 5.27 -> 5.63Hurt
optimize NR-IQA score in discrete codebook space instead of continuous space (ablation)quality optimization · Fig. 7 visual studyhuman-perceived realismImproved
plug quality prior into WaveFaceWaveFace · LFW-TestTOPIQ-G: 0.786 -> 0.802Improved
plug quality prior into InterlcmInterlcm · LFW-TestTOPIQ-G: 0.831 -> 0.850Improved
plug quality prior into Reti-DiffReti-Diff · LOL-v1FID: 49.14 -> 42.15Improved
plug quality prior into CIDNetCIDNet · LOL-v2-realFID: 48.04 -> 43.33Improved
plug quality prior into CIDNet for detectionCIDNet · ExDarkmean AP: 73.6 -> 75.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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