Research map / Image generation / Editing and style transfer
LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup
Qiao Gu, Guanzhi Wang, Mang Tik Chiu, Yu-Wing Tai, Chi-Keung Tang
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 local style discriminators (K=3) over a single global discriminator (ablation) | LADN · Extreme makeup dataset (qualitative) | visual makeup quality | Improved |
| increase local discriminators from K=6 to K=12 (ablation) | LADN · Extreme makeup dataset (qualitative) | visual makeup quality | Improved |
| add local high-order loss (ablation) | LADN · Extreme makeup dataset (qualitative) | visual makeup quality | Improved |
| add smooth loss for makeup removal (ablation) | LADN · Extreme makeup dataset (qualitative) | visual makeup quality | Improved |
Closest papers by meaning
- PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup (CVPR 2018 · similarity 0.89)
- Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification (AAAI 2018 · similarity 0.88)
- Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features (CVPR 2026 · similarity 0.88)
- Neural Face Editing With Intrinsic Image Disentangling (CVPR 2017 · similarity 0.87)
- PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal (TPAMI 2021 · similarity 0.87)
- DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection (CVPR 2024 · similarity 0.86)
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.
