AI Paper Atlas

Research map / Image generation / Editing and style transfer

StyleSwap: Style-Based Generator Empowers Robust Face Swapping

Zhiliang Xu, Hang Zhou, Zhibin Hong, Ziwei Liu, Jiaming Liu, Zhizhi Guo, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang

ECCV 2022 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 49 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 spatial feature maps instead of a style vector (ablation)StyleSwap · FF++ID Retrieval: 96.68% -> 97.05%Improved
add spatial feature maps instead of a style vector (ablation)StyleSwap · FF++Pose error: 2.81 -> 1.56Improved
add spatial feature maps instead of a style vector (ablation)StyleSwap · FF++FID: 4.54 -> 2.72Improved
add the mask branch (ablation)StyleSwap · FF++ID Retrieval: 95.56% -> 97.05%Improved
add the mask branch (ablation)StyleSwap · FF++FID: 3.18 -> 2.72Improved
add the mask branch (ablation)StyleSwap · FF++Exp. error: 5.78 -> 5.28Improved
add W-space swapping-driven ID inversion (ablation)StyleSwap · FF++ID Cosine: 0.677 -> 0.693Improved
use W+ instead of W for ID inversion (ablation)StyleSwap · FF++ID Cosine: 0.693 -> 0.706Improved
use W+ instead of W for ID inversion (ablation)StyleSwap · FF++FID: 2.60 -> 2.58Improved
add ID inversion in W+ space (ablation)StyleSwap · FF++Pose error: 1.56 -> 1.51No clear effect
add 50,000 StyleSwap fakes to detector trainingXception detector · Celeb-DFAUC: 66.60 -> 73.59Improved
add 50,000 StyleSwap fakes instead of FaceShifter fakesXception detector · Celeb-DFAUC: 71.92 -> 73.59Improved

Later papers that compared with this method

1 later accepted paper reports StyleSwap as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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