AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

PIE: Physics-Inspired Low-Light Enhancement

Dong Liang, Zhengyan Xu, Ling Li, Mingqiang Wei, Songcan Chen

IJCV 2024 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 28 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 contrastive loss L_c (ablation)PIE · Average of five test setsNIQE: 4.38 -> 3.38Improved
add regional brightness consistency loss L_rc (ablation)PIE · Average of five test setsNIQE: 3.45 -> 3.38Improved
add feature retention loss L_fr (ablation)PIE · Average of five test setsNIQE: 3.53 -> 3.38Improved
add negative samples (ablation)PIE · Average of five test setsUNIQUE: 0.78 -> 0.95Improved
add overexposed negatives (ablation)PIE · Average of five test setsUNIQUE: 0.74 -> 0.95Improved
add underexposed negatives (ablation)PIE · Average of five test setsNIQE: 4.38 -> 3.38Improved
use mixed Bag of Curves instead of gamma curves only (ablation)PIE · Average of five test setsNIQE: 3.39 -> 3.38No clear effect
use mixed Bag of Curves instead of logarithmic curves only (ablation)PIE · Average of five test setsNIQE: 3.47 -> 3.38Improved
use InfoNCE instead of triplet loss for contrastive learning (ablation)PIE · SICE Part2PSNR: 18.44 -> 19.79Improved
use InfoNCE instead of N-pair loss (ablation)PIE · SICE Part2PSNR: 15.08 -> 19.79Improved
use 5 negatives per positive instead of 1 (ablation)PIE · Average of five test setsNIQE: 3.38 -> 3.37; time 73.6 -> 131.3 minNo clear effect
use 5 positives per negative instead of 1 (ablation)PIE · Average of five test setsNIQE: 3.38 -> 3.46Hurt

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