Research map / Image generation / Editing and style transfer
Fast Face-Swap Using Convolutional Neural Networks
Iryna Korshunova, Wenzhe Shi, Joni Dambre, Lucas Theis
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 the lighting loss term to the objective (ablation) | CageNet · qualitative face swap | lighting preservation (visual) | Improved |
| increase style weight alpha from 80 to 120 (ablation) | CageNet 256x256 · qualitative face swap | expression preservation (visual): 80 -> 120 | Mixed |
| use only the best N_best style images (similar pose) instead of all (ablation) | multi-image patch style loss · qualitative face swap | visual quality | Improved |
| replace the transformation network with nearest-landmark style image lookup (ablation) | face swap pipeline · qualitative face swap | expression and blending (visual) | Hurt |
| train for a different target identity (Taylor Swift) with same hyperparameters | CageNet · qualitative face swap | visual quality | No clear effect |
Closest papers by meaning
- Fine-Grained Face Swapping via Regional GAN Inversion (CVPR 2023 · similarity 0.90)
- DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors (ICCV 2025 · similarity 0.89)
- Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness (CVPR 2022 · similarity 0.89)
- High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning (CVPR 2026 · similarity 0.89)
- Learning Disentangled Representation for One-Shot Progressive Face Swapping (TPAMI 2024 · similarity 0.88)
- FSGAN: Subject Agnostic Face Swapping and Reenactment (ICCV 2019 · similarity 0.88)
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.
