AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

PieNet: Personalized Image Enhancement Network

Han-Ul Kim, Young Jun Koh, Chang-Su Kim

ECCV 2020 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 57 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
use personalized preference vectors instead of a single-style enhancerPieNet · MIT-Adobe 5K multiple usersmPSNR: 24.28 vs 21.74 (DUPE)Improved
test on all five photographers instead of C onlyDUPE · MIT-Adobe 5KPSNR: 23.61 -> 21.74Hurt
test on all five photographers instead of C onlyPieNet · MIT-Adobe 5KPSNR: 25.28 -> 24.28Hurt
train with supervised paired data rather than unpaired dataHDR/DPE/DUPE vs WB/D&R · MIT-Adobe 5K single userPSNR: 18.36 -> 23.61Improved
add the perceptual loss based on the embedding network (ablation)PieNet · MIT-Adobe 5K single userPSNRImproved
use triplet-loss preference vector scheme with many preferred images (Npref=2000) instead of feature averaging (ablation)PieNet · Expanded MIT-Adobe 5K, 8 new usersmPSNRImproved
use triplet-loss preference vector scheme with few preferred images instead of feature averaging (ablation)PieNet · Expanded MIT-Adobe 5K, 8 new usersmPSNRHurt
use feature averaging with only 20 preferred images (ablation)PieNet · Expanded MIT-Adobe 5K, 8 new usersmPSNRNo clear effect

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