AI Paper Atlas

Research map / Image generation / Editing and style transfer

StyleFace: Towards Identity-Disentangled Face Generation on Megapixels

Yuchen Luo, Junwei Zhu, Keke He, Wenqing Chu, Ying Tai, Chengjie Wang, Junchi Yan

ECCV 2022 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 24 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 StyleFace instead of InfoSwap for swappingInfoSwap · Identity swapping (FF++ / CelebAMaskHQ)FID (CelebAMaskHQ): 3.39 -> 2.04Improved
use StyleFace instead of InfoSwap for swappingInfoSwap · Identity swapping (FF++ / CelebAMaskHQ)ID retrieval: 98.70 -> 96.34Hurt
use StyleFace instead of InfoSwap for swappingInfoSwap · Identity swapping (FF++ / CelebAMaskHQ)pose error: 3.11 -> 2.52Improved
use StyleFace instead of InfoSwap for swappingInfoSwap · Identity swapping (FF++ / CelebAMaskHQ)inference time (ms per 1024^2 image): 329 -> 86Improved
use StyleFace instead of InfoSwap for swappingInfoSwap · Identity swapping (FF++ / CelebAMaskHQ)user study preference (%): 18.7% -> 74.6%Improved
use StyleFace instead of CIAGAN for de-identificationCIAGAN · De-identification (LFW, TAR, VGGFace2 FaceNet)true acceptance rate: 0.034 -> 0.013Improved
use StyleFace instead of CIAGAN for de-identificationCIAGAN · De-identification (LFW, TAR, CASIA FaceNet)true acceptance rate: 0.019 -> 0.012Improved
expand latent space Z to Z+ (hierarchical codes) (ablation)StyleFace · Identity swapping (qualitative)identity similarityImproved
add contrastive constraint on W+ codes (ablation)StyleFace · Virtual identity sampling (t-SNE)feasibility of sampled identitiesImproved

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