AI Paper Atlas

Research map / Image generation / Image restoration

Towards Illumination-Aware Restoration of Metalens-Captured Images: A New Dataset and a Strong Baseline

Fen Fang, Xinan Liang, Muli Yang, Jinghong Zheng, Tobias Mass, Ying Sun, Xulei Yang, Xuewu Xu, Zhengguo Li

AAAI 2026 · Image generation › Image restoration · approach: Image harmonization and color transformation · 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 Spatial-Aware Attention Scheduler (M1) (ablation)DRMI · IlluMeta Setup 1 (avg)PSNR (dB), whole: 16.8 -> 17.3Improved
add Spatial-Aware Attention Scheduler (M1) (ablation)DRMI · IlluMeta Setup 1 (avg)PSNR (dB), peripheral: 14.4 -> 15.3Improved
add Retraining-Free Illumination Adapter (M2) (ablation)DRMI · IlluMeta Setup 1 (avg)PSNR (dB), whole: 16.8 -> 18.2Improved
add both M1 and M2 (ablation)DRMI · IlluMeta Setup 1 (avg)PSNR (dB), whole: 18.2 -> 18.8Improved
add M1 on top of M2 for peripheral area (ablation)DRMI · IlluMeta Setup 1 (avg)PSNR (dB), peripheral: 16.5 -> 16.6No clear effect
add Attention SchedulerDRMI · DIV2K-Meta whole imagePSNR (dB): 22.09 -> 22.17No clear effect
add Attention SchedulerDRMI · DIV2K-Meta peripheralPSNR (dB): 16.56 -> 17.46Improved
add Attention SchedulerSFNet · DIV2K-Meta whole imagePSNR (dB): 18.22 -> 18.47No clear effect
train the restoration model jointly on multiple ILs instead of one IL (ablation)restoration model · IlluMetaPSNR (dB): 24.20 -> 22.71Hurt
add RL illumination adapter instead of joint multi-IL trainingDRMI · IlluMeta Setup 1 (avg)PSNR (dB): 16.8 -> 18.8Improved
add RL illumination adapter instead of joint multi-IL trainingNAFNet · IlluMeta Setup 1 (avg)PSNR (dB): 19.7 -> 19.9No clear effect
add RL illumination adapter instead of joint multi-IL trainingHINet · IlluMeta Setup 1 (avg)PSNR (dB): 19.9 -> 21.0Improved

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