Research map / Image generation / Editing and style transfer
Style Transformer for Image Inversion and Editing
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Style Transformer instead of pSp inversion | StyleGAN2 face inversion · CelebA-HQ test | MSE: 0.037 -> 0.036 | Helped |
| Use Style Transformer instead of pSp inversion | StyleGAN2 face inversion · CelebA-HQ test | LPIPS: 0.169 -> 0.166 | Helped |
| Use Style Transformer instead of pSp inversion | StyleGAN2 face inversion · CelebA-HQ test | FID: 31.52 -> 28.31 | Helped |
| Use Style Transformer instead of pSp inversion | StyleGAN2 face inversion · CelebA-HQ test | SWD: 15.07 -> 14.00 | Helped |
| Use Style Transformer instead of pSp inversion | StyleGAN2 face editing · CelebA-HQ test, edited | FID: 46.64 -> 40.57 | Helped |
| Use Style Transformer instead of pSp inversion | StyleGAN2 face editing · CelebA-HQ test, edited | SWD: 29.05 -> 23.21 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car inversion · Stanford Cars | MSE: 0.110 -> 0.089 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car inversion · Stanford Cars | LPIPS: 0.314 -> 0.245 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car inversion · Stanford Cars | FID: 14.68 -> 13.58 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car inversion · Stanford Cars | SWD: 18.25 -> 16.14 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car editing · Stanford Cars, edited | FID: 21.50 -> 21.24 | Helped |
| Use Style Transformer instead of e4e inversion | StyleGAN2 car editing · Stanford Cars, edited | SWD: 27.57 -> 25.28 | Helped |
Closest papers by meaning
- ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing (AAAI 2023 · similarity 0.93)
- Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint (CVPR 2023 · similarity 0.92)
- The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · similarity 0.91)
- Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · similarity 0.89)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.86)
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting (NeurIPS 2025 · 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.