AI Paper Atlas

Research map / Image generation / Editing and style transfer

CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing

Xuanhong Chen, Bingbing Ni, Naiyuan Liu, Ziang Liu, Yiliu Jiang, Loc Truong, Qi Tian

ECCV 2020 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 14 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 skip connections (0 to 4) (ablation)U-Net style editor · CelebAPSNR: 20.2 -> 34.8Improved
add skip connections (0 to 4) (ablation)U-Net style editor · CelebAaverage attribute editing accuracy: 89.5% -> 63.9%Hurt
add the global module to the local module (ablation)CooGAN · CelebA-HQ 768x768qualitative attribute editingImproved
replace STU with LSTU (ablation)LSTU-Net · skip connection (16 in-channel)parameters: 1.63M -> 0.81MImproved
replace STU with LSTU (ablation)LSTU-Net · skip connection (16 in-channel)FLOPS: 5.06G -> 2.02GImproved
replace STU with LSTU (ablation)LSTU-Net · skip connection (64 in-channel)FLOPS: 79.50G -> 30.80GImproved
replace STU with LSTU (ablation)STGAN · CelebA 128x128 reconstructionPSNR: 31.6 -> 32.1No clear effect
replace STU with LSTU (ablation)STGAN · CelebA 128x128 reconstructionSSIM: 0.934 -> 0.938No clear effect
use patch-based CooGAN instead of AttGAN-HRCooGAN · CelebA-HQ 768x768GPU memory: 3692 MB -> 985 MBImproved
use patch-based CooGAN instead of STGAN-HRCooGAN · CelebA-HQ 768x768GPU memory: 6306 MB -> 985 MBImproved
use patch-based CooGAN instead of STGAN-HRCooGAN · CelebA-HQ 768x768inference time: 0.0502 s -> 0.0645 sHurt
use CooGAN instead of STGAN-HRCooGAN · User study Male attributeuser preference: 51.3% -> 87.9%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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