AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

Han Zhou, Wei Dong, Xiaohong Liu, Shuaicheng Liu, Xiongkuo Min, Guangtao Zhai, Jun Chen

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 77 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 the adaptive feature transformation (AFT) module to SimGLARE (ablation)GLARE · LOL-v1PSNR: 26.51 -> 27.35Improved
add dual-decoder architecture on top of AMB (ablation)GLARE · LOL-v1PSNR: 26.60 -> 27.35Improved
use adaptive mix-up block instead of skip connection (ablation)GLARE · LOL-v1PSNR: 26.88 -> 27.35Improved
train with NLL loss instead of L1 loss (ablation)SimGLARE · LOL-v1PSNR: 25.69 -> 26.51Improved
use I-LNF instead of Transformer code-index prediction (ablation)SimGLARE (L1) · LOL-v1PSNR: 25.12 -> 25.69Improved
add the I-LNF module (ablation)SimGLARE (L1) · LOL-v1PSNR: 24.53 -> 25.69 (1.16 dB)Improved
add the normal-light codebook prior (ablation)SimGLARE (L1) · LOL-v1PSNR: 23.42 -> 25.69Improved
add perceptual loss to L1 in stage III (ablation)GLARE · LOL-v1PSNR: 27.02 -> 27.09Improved
add SSIM loss to L1 + perceptual in stage III (ablation)GLARE · LOL-v1PSNR: 27.09 -> 27.35Improved
use GLARE as low-light enhancement preprocessing for detectionYOLO-v3 on ExDark · ExDark detectionmAP: 76.32 -> 77.50Improved
GLARE versus competing methods on unpaired datasetsGLARE · LIME and NPE (NIQE)NIQE: LIME 4.52 vs RFR 3.81; NPE 4.19 vs LL-SKF 4.08Mixed

Later papers that compared with this method

2 later accepted papers report GLARE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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