AI Paper Atlas

Research map / Image generation / Editing and style transfer

Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness

Jiseob Kim, Jihoon Lee, Byoung-Tak Zhang

CVPR 2022 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 46 citations (OpenAlex)

Check 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 a supervised-contrastive smooth identity embedder instead of ArcFace (ablation)Smooth-Swap · FaceForensics++Overall: -0.617 vs -0.329Improved
train for 50% of the steps (ablation)Smooth-Swap · FaceForensics++Overall: -0.617 -> -0.398Hurt
reduce identity-loss weight to lambda_id=1 (ablation)Smooth-Swap with the proposed embedder · FaceForensics++Overall: -0.617 -> -0.419Hurt
use ArcFace instead of the proposed embedder with lambda_id=1 (ablation)Smooth-Swap generator · FaceForensics++Overall: -0.617 -> 0.266Hurt
use ArcFace instead of the proposed embedder with lambda_id=4 (ablation)Smooth-Swap generator · FaceForensics++Overall: -0.617 -> 0.699Hurt
use the proposed contrastive embedder rather than ArcFace (ablation)Smooth-Swap generator · FaceForensics++ trainingidentity-loss convergence speedImproved
use the proposed contrastive embedder rather than ArcFace (ablation)Smooth-Swap generator · FaceForensics++ trainingchange-loss stabilityImproved
use the proposed contrastive embedder rather than ArcFaceidentity embedding · FFHQ test splitd_smooth (r=0.25, samples): 0.360 -> 0.116Improved
use the proposed contrastive embedder rather than ArcFaceidentity embedding · FFHQ test splitd_smooth (r=0.5, samples): 0.380 -> 0.135Improved
use the proposed contrastive embedder rather than ArcFaceidentity embedding · StyleGAN2-generated facesd_smooth (r=0.5, GAN): 0.802 -> 0.671Improved
use the proposed contrastive embedder rather than ArcFaceidentity embedding · LFWVerification AUC: 0.995 -> 0.999No clear effect

Later papers that compared with this method

1 later accepted paper reports SmoothSwap 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