AI Paper Atlas

Research map / Image generation / Image restoration

Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge

Xiaogang Xu, Jiafei Wu, Qingsen Yan, Jiequan Cui, Richang Hong, Bei Yu

ICCV 2025 · Image generation › Image restoration · approach: Low-light image enhancement · 3 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 sample-updater (SU) when learning LFPVs (ablation)SNR+LFPVs · SIDPSNR: 22.96 -> 23.15Improved
add mutual-updater (MU) when learning LFPVs (ablation)SNR+LFPVs · SIDPSNR: 22.88 -> 23.15Improved
add identity embedding to LFPVs (ablation)SNR+LFPVs · SIDPSNR: 22.94 -> 23.15Improved
place LFPVs in encoder instead of decoder (ablation)SNR+LFPVs · SIDPSNR: 23.09 -> 23.15Improved
increase LFPVs from 8 to 16 (ablation)SNR+LFPVs · SIDPSNR: 22.97 -> 23.15Improved
increase LFPVs from 16 to 32 (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 23.29Improved
double layers of SU and MU (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 23.30Improved
train SU with hard samples instead of random (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 22.92Mixed
increase patch size from 4 to 8 (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 22.81Mixed
train LLIE then LFPVs in order instead of jointly (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 23.39Improved
implement SU and MU with LSTM instead of CNN (ablation)SNR+LFPVs · SIDPSNR: 23.15 -> 23.85Improved
add LFPVs to RestormerRestormer · SIDPSNR: 22.27 -> 23.60Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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