AI Paper Atlas

Research map / Image generation / Image restoration

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

Kun Zhou, Xinyu Lin, Wenbo Li, Xiaogang Xu, Yuanhao Cai, Zhonghang Liu, Xiaoguang Han, Jiangbo Lu

ECCV 2024 · Image generation › Image restoration · approach: Low-light image enhancement · 9 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
apply frequency-disentangled coarse-to-fine training (ACCA + LDRM) to existing LLIE modelsRestormer · SDSD-outPSNR (dB): 24.79 -> 32.47Improved
apply the disentanglement schemeRetinexformer · SIDPSNR (dB): 24.44 -> 24.64Improved
apply the disentanglement scheme to all six baselinesMIR-Net, Restormer, LLFlow, SNR, Retinexformer, Diff-L · LOL-v2, SID, SDSD, SMIDPSNR (dB): 20.02 -> 24.19 (MIR-Net, LOL-v2)Improved
use the frequency-disentangled scheme instead of segmentation-guided SKFSNR · LOL-v2PSNR (dB): 21.93 (SKF) -> 24.00Improved
add low-frequency consistent loss L_i (ablation)Restormer + ACCA · LOL-v2PSNR (dB): 20.21 -> 24.56Improved
add ACCA and LDRM without L_i (ablation)Restormer · LOL-v2PSNR (dB): 19.94 -> 20.21No clear effect
freeze ACCA (decoupled optimization) instead of end-to-end training (ablation)LLFlow · LOL-v2PSNR (dB): 27.94 -> 28.90Improved
replace ACCA with ZeroDCE, Star, PairLIE or IAT as coarse module (ablation)Restormer · LOL-v2PSNR (dB): ZeroDCE 21.53, IAT 23.97 vs ACCA 24.56Mixed
use four Laplacian pyramid levels rather than 3, 5 or 6 (ablation)LDRM · LOL-v2PSNR (dB)Improved
add the method to existing modelssix LLIE baselines · model complexityparameters: +0.088M params, +2.53 GFLOPS, +0.008sImproved

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