AI Paper Atlas

Research map / Image generation / GANs

Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs

Yu-Sheng Chen, Yu-Ching Wang, Man-Hsin Kao, Yung-Yu Chuang

CVPR 2018 · Image generation › GANs · approach: Stabilized GAN training · 498 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 global features to U-Net (ablation)U-Net for MIT-Adobe 5K photographer retouching prediction · MIT-Adobe 5K testPSNR: 22.13 -> 23.80Improved
Add global features to U-Net (ablation)U-Net for MIT-Adobe 5K photographer retouching prediction · MIT-Adobe 5K testSSIM: 0.879 -> 0.900Improved
Use global U-Net instead of U-Net (ablation)local Laplacian approximation · MIT-Adobe 5K testPSNR: 31.06 -> 33.93Improved
Replace WGAN-GP gradient penalty with the adaptive A-WGAN penalty and weighting (ablation)One-way GAN enhancement · MIT-Adobe 5K testPSNR: 21.42 -> 22.17Improved
Vary the WGAN-GP gradient-penalty weight λ (ablation)WGAN-GP enhancement · MIT-Adobe 5K testPSNR: 21.42; 21.19; 20.78Mixed
Use a two-way GAN instead of a one-way GAN (ablation)WGAN-GP enhancement · MIT-Adobe 5K testPSNR: 21.42 -> 21.96Improved
Use a two-way GAN instead of a one-way GAN (ablation)A-WGAN enhancement · MIT-Adobe 5K testPSNR: 22.17 -> 22.21Improved
Give the two generators individual batch-normalization layers (ablation)2-way WGAN-GP · MIT-Adobe 5K testPSNR: 21.96 -> 22.27Improved
Give the two generators individual batch-normalization layers (ablation)2-way A-WGAN · MIT-Adobe 5K testPSNR: 22.21 -> 22.37Improved
Use A-WGAN's adaptive weighting rather than fixed WGAN-GP weighting (ablation)GAN training on the swissroll distribution · swissrollconvergenceImproved
Train the image enhancer using the HDR photograph set rather than MIT-Adobe 5K retouching labelsDeep Photo Enhancer · photographic image enhancementuser preference: 81% (323 among 400)Improved
Remove individual batch normalization (ablation)HDR-trained 2-way GAN enhancer · photographic image enhancementvisual color renditionHurt

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