Research map / Image generation / Editing and style transfer
Learning Disentangled Representation for One-Shot Progressive Face Swapping
Qi Li, Weining Wang, Chengzhong Xu, Zhenan Sun, Ming–Hsuan Yang
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 |
|---|---|---|---|
| use the learned flexible identity encoder instead of a fixed ArcFace identity vector (ablation) | FaceSwapper · FaceForensics++ | pose error: 3.09 -> 2.10 | Improved |
| use the learned identity encoder instead of a fixed ArcFace vector (ablation) | FaceSwapper · FaceForensics++ | ID retrieval: 95.56 -> 94.48 | Hurt |
| add semantic mask information in the SDL (ablation) | FaceSwapper · FaceForensics++ | ID retrieval: 1.20 -> 94.48 | Improved |
| add semantic mask information in the SDL (ablation) | FaceSwapper · FaceForensics++ | pose error: 3.83 -> 2.10 | Improved |
| add landmark information in the SDL (ablation) | FaceSwapper · FaceForensics++ | pose error: 3.75 -> 2.10 | Improved |
| add landmark information in the SDL (ablation) | FaceSwapper · FaceForensics++ | expression error: 3.50 -> 2.69 | Improved |
| add reconstruction loss (ablation) | FaceSwapper · FaceForensics++ | ID retrieval: 90.14 -> 94.48 | Improved |
| add identity preservation loss (ablation) | FaceSwapper · FaceForensics++ | ID retrieval: 0.24 -> 94.48 | Improved |
| add attribute preservation loss (ablation) | FaceSwapper · FaceForensics++ | ID retrieval: 89.30 -> 94.48 | Improved |
| add adversarial loss (ablation) | FaceSwapper · FaceForensics++ | pose error: 7.84 -> 2.10 | Improved |
| add adversarial loss (ablation) | FaceSwapper · FaceForensics++ | expression error: 3.72 -> 2.69 | Improved |
| add identity preservation loss (ablation) | FaceSwapper · FaceForensics++ | pose error: 1.80 -> 2.10 | Hurt |
Closest papers by meaning
- Reinforced Disentanglement for Face Swapping without Skip Connection (ICCV 2023 · similarity 0.93)
- High-Resolution Face Swapping via Latent Semantics Disentanglement (CVPR 2022 · similarity 0.91)
- Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping (ECCV 2022 · similarity 0.91)
- High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning (CVPR 2026 · similarity 0.91)
- BlendFace: Re-designing Identity Encoders for Face-Swapping (ICCV 2023 · similarity 0.91)
- Information Bottleneck Disentanglement for Identity Swapping (CVPR 2021 · similarity 0.90)
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.
