Research map / Image generation / Editing and style transfer
StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN
Read the paperCheck 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 StyleRes instead of competing inversion methods | StyleGAN2 real-image inversion · CelebA-HQ reconstruction | FID: 11.33 -> 7.04 | Helped |
| Use StyleRes instead of competing inversion methods | StyleGAN2 real-image inversion · CelebA-HQ smile addition | FID: 25.22 -> 23.52 | Helped |
| Use StyleRes instead of competing inversion methods | StyleGAN2 real-image inversion · Stanford Cars reconstruction | LPIPS: 0.16 -> 0.14 | Helped |
| Use StyleRes instead of competing inversion methods | StyleGAN2 real-image inversion · Stanford Cars grass edit | FID: 14.84 -> 10.64 | Helped |
| Add learned high-rate residual features and their edit-conditioned transformation (ablation) | StyleRes · Real-image pose editing | edit detail preservation | Helped |
| Add the E1 residual-feature encoder (ablation) | StyleRes · Real-image pose editing | edit detail preservation | Helped |
| Add the E2 edit-conditioned feature transformation module (ablation) | StyleRes · Real-image pose editing | edit quality | Helped |
| Add cycle consistency loss (ablation) | StyleRes · Real-image attribute editing | detail preservation | Helped |
Closest papers by meaning
- Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint (CVPR 2023 · similarity 0.94)
- The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · similarity 0.94)
- Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · similarity 0.90)
- Tuning-Free Inversion-Enhanced Control for Consistent Image Editing (AAAI 2024 · similarity 0.88)
- DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing (NeurIPS 2025 · similarity 0.87)
- Object-Aware Inversion and Reassembly for Image Editing (ICLR 2024 · similarity 0.87)
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.