Research map / Image generation / Editing and style transfer
Spatially-Adaptive Multilayer Selection for GAN 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 spatially-adaptive multilayer selection instead of a single latent space | StyleGAN2 inversion · Cars | LPIPS: 0.24 -> 0.16 | Helped |
| Use spatially-adaptive multilayer selection instead of a single latent space | StyleGAN2 inversion · Cars | PSNR: 19.39 -> 22.81 | Helped |
| Use spatially-adaptive multilayer selection | Encoder-based StyleGAN2 inversion · Cars | PSNR: 16.44 -> 19.21 | Helped |
| Use spatially-adaptive multilayer selection | Encoder-based StyleGAN2 inversion · Faces | LPIPS: 0.29 -> 0.29 | No clear effect |
| Add feature-space regularization L_F (ablation) | SAM inversion · Image editing | editability | Helped |
| Refine the invertibility map using semantic segments (ablation) | SAM inversion · Image editing | edit coherence | Helped |
| Use predicted invertibility instead of fixed car/background class assignments (ablation) | SAM inversion · Car reconstruction and editing | reconstruction quality | Helped |
| Use LPIPS-VGG instead of LPIPS-AlexNet (ablation) | SAM inversion · Car images | perceptual reconstruction quality | Helped |
Closest papers by meaning
- ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing (AAAI 2023 · similarity 0.91)
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting (NeurIPS 2025 · similarity 0.90)
- Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · similarity 0.89)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.89)
- Spatial-Contextual Discrepancy Information Compensation for GAN Inversion (AAAI 2024 · similarity 0.88)
- The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 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.