atlas

Research map / Image generation / Editing and style transfer

Spatially-Invariant Style-Codes Controlled Makeup Transfer

CVPR 2021 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 79 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 spatially invariant part-specific style-codes instead of pixel-wise correspondenceSCGAN · Makeup Transfer (MT) dataset; misaligned and rotated facesvisual quality and transfer correctnessHelped
Add an MLP to map initial style-code Z into W (ablation)SCGAN · Part-specific lip makeup transferpart-specific disentanglementHelped
Use AdaIN layers in all three fusion blocks instead of only the first block (ablation)SCGAN · Part-specific lip makeup transfermakeup transfer strengthHelped
Add local perceptual loss (ablation)SCGAN · Makeup Transfer (MT) datasetlocal consistency and visual qualityHelped
Use SCGAN rather than BeautyGAN, LADN, or PSGANMakeup transfer · Aligned, misaligned, and rotated image pairsuser preference for visual quality and precise transferHelped

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