Research map / Image generation / Editing and style transfer
PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal
Si Liu, Wentao Jiang, Chen Gao, Ran He, Jiashi Feng, Bo Hu Li, Shuicheng Yan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add makeup detail loss (PSGAN++ over PSGAN) | PSGAN · MT user study | ratio selected as best (%): 33.50 -> 47.50 | Improved |
| add makeup detail loss (PSGAN++ over PSGAN) | PSGAN · MT-Wild user study | ratio selected as best (%): 37.50 -> 50.25 | Improved |
| add makeup detail loss (PSGAN++ over PSGAN) | PSGAN · MT-HR user study | ratio selected as best (%): 38.25 -> 51.50 | Improved |
| add makeup detail loss | PSGAN · MT identity preservation | FID: 41.98 -> 41.17 | Improved |
| add makeup detail loss | PSGAN · MT identity preservation | ArcFace similarity: 0.9721 -> 0.9726 | No clear effect |
| add makeup detail loss | PSGAN · MT landmark preservation | cos_sim: 0.9992 -> 0.9992 | No clear effect |
| add attentive makeup morphing (AMM) module (ablation) | PSGAN++ · pose/expression-varied faces | qualitative | Improved |
| add visual features (weight 0.01) to the AMM attention (ablation) | PSGAN++ · attention maps | qualitative | Improved |
| increase the visual feature weight in AMM attention (ablation) | PSGAN++ · attention maps | qualitative | Hurt |
| use PSGAN++ for makeup removal instead of DRL | DRL · CMF face verification | TPR@FPR=0.1%: 71.07 -> 77.44 | Improved |
| use PSGAN++ for makeup removal instead of DRL | DRL · CMF face verification | Rank-1: 93.08 -> 93.27 | Improved |
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.
- PSGAN — PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer (CVPR 2020) · better on 5 of 6 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
- PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer (CVPR 2020 · similarity 0.95)
- Spatially-Invariant Style-Codes Controlled Makeup Transfer (CVPR 2021 · similarity 0.91)
- Makeup Prior Models for 3D Facial Makeup Estimation and Applications (CVPR 2024 · similarity 0.87)
- SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models (NeurIPS 2024 · similarity 0.87)
- Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth (CVPR 2024 · similarity 0.86)
- Recoverable Facial Identity Protection via Adaptive Makeup Transfer Adversarial Attacks (AAAI 2025 · similarity 0.85)
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.
