AI Paper Atlas

Research map / Image generation / Image restoration

Difficulty-Conditioned Attribute-Specific Restoration for Low-Light Image Enhancement

Mingzhu Zhang, Shuang Li, Jiaxu Leng, Long Sun, Can Zhang, Miaoqing Wang, Xinbo Gao

ECCV 2026 · Image generation › Image restoration · approach: Low-light image enhancement · 0 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 GIM to baseline (ablation)U-Net/CIDNet-style baseline · LOL-v2-realPSNR: 23.498 -> 23.625Improved
add SRM to baseline (ablation)baseline · LOL-v2-realPSNR: 23.498 -> 23.765Improved
add both GIM and SRM (ablation)baseline · LOL-v2-realPSNR: 23.498 -> 23.894Improved
add adaptive prior-weighted loss Lapw (ablation)DCASR with GIM and SRM · LOL-v2-realPSNR: 23.894 -> 24.053Improved
use GIM in I branch and SRM in HV branch instead of channel attention (ablation)DCASR · LOL-v2-realPSNR: 23.012 -> 23.894Improved
place GIM in I branch and SRM in HV branch rather than swapped (ablation)DCASR · LOL-v2-realPSNR: 22.662 -> 23.894Improved
use heterogeneous GIM+SRM rather than dual GIM (ablation)DCASR · LOL-v2-realPSNR: 22.923 -> 23.894Improved
use heterogeneous GIM+SRM rather than dual SRM (ablation)DCASR · LOL-v2-realPSNR: 22.241 -> 23.894Improved
use diffusion-predicted difficulty prior instead of no prior (ablation)DCASR · LOL-v2-realPSNR: 23.498 -> 24.053Improved
use residual-derived diffusion prior instead of confidence map guidance (ablation)DCASR · LOL-v2-realPSNR: 23.768 -> 24.053Improved
use SNR map as prior guidance instead of no prior (ablation)DCASR · LOL-v2-realPSNR: 23.498 -> 23.129Hurt
use diffusion to predict prior instead of transformer (ablation)DCASR · LOL-v2-realPSNR: 23.611 -> 24.053Improved

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