AI Paper Atlas

Research map / Image generation / Editing and style transfer

Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer

Bo Wei, Xianhui Lin, Yi Dong, Zhongzhong Li, Zonghui Li, Zirui Wang, Jiachen Yang, Xing Liu, Hong Gu, Xiaoming Li, Wangmeng Zuo

ECCV 2026 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 0 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 Stage II reality-anchored refinement to Stage I (ablation)ART · MF2K test setMSim_G: 8.82 -> 9.22Improved
add Stage II refinement to Stage I (ablation)ART · MF2K test setID similarity: .57 -> .74Improved
add Stage I initialization to Stage II (ablation)ART · MF2K test setMSim_G: 8.08 -> 9.22Improved
add Stage I initialization to Stage II (ablation)ART · MT test setMSim_Q: 5.35 -> 7.12Hurt
add Stage II refinement to Stage I (ablation)ART · MF2K test setL2-M: 7.68 -> 4.31Improved
add Stage II refinement to Stage I (ablation)ART · MT test setFID: 84.93 -> 87.72Hurt
train on StableMakeup pseudo-targets instead of Nano Banana Pro (ablation)ART · MF2K test setMSim_G: 9.22 -> 8.56Hurt
apply ART refinement on StableMakeup pseudo-targets vs StableMakeup (ablation)ART (SM pseudo-targets) · MF2K test setMSim_G: 6.73 -> 8.56Improved
retrain StableMakeup on MF2K data (ablation)StableMakeup · MF2K test setMSim_G: 6.73 -> 6.58No clear effect
retrain StableMakeup on MF2K data (ablation)StableMakeup · MT test setMSim_G: 8.34 -> 8.47Improved
add ~4,500 unpaired images to Stage II refinement (ablation)ART · MF2K test setMSim_G: 9.14 -> 9.22Improved
increase residual makeup alpha in bare-skin anchor from 0.00 to 0.10 (ablation)ART · Four test sets (average)MSim_G: 9.02 -> 8.84Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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