Research map / Image generation / Editing and style transfer
High-Fidelity GAN Inversion for Image Attribute 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 |
|---|---|---|---|
| Add distortion consultation to the low-rate e4e encoder | e4e inversion on CelebA-HQ · CelebA-HQ first 1,500 images | MAE: .0919±.0008 -> .0617±.0004 | Helped |
| Add distortion consultation to the low-rate e4e encoder | e4e inversion on CelebA-HQ · CelebA-HQ first 1,500 images | SSIM: .742±.007 -> .877±.002 | Helped |
| Add distortion consultation to the low-rate e4e encoder | e4e inversion on CelebA-HQ · CelebA-HQ first 1,500 images | LPIPS: .221±.003 -> .127±.001 | Helped |
| Add distortion consultation to the low-rate e4e encoder | e4e inversion on CelebA-HQ · CelebA-HQ first 1,500 images | inference time: 0.11s -> 0.24s | Hurt |
| Add distortion consultation to the low-rate encoder (ablation) | GAN inversion and editing · Face and car domains | image-specific detail preservation | Helped |
| Add adaptive distortion alignment (ADA) before consulting distortion during editing (ablation) | DCI attribute editing · Face and car image editing | generated image quality | Helped |
| Replace feature-space alignment and fusion with image-space distortion addition without warping (ablation) | DCI attribute editing · Image editing | artifact-free image quality | Hurt |
| Use landmark-based warping and image-space fusion instead of ADA and consultation fusion (ablation) | DCI attribute editing · Image editing | artifact-free image quality | Hurt |
| Apply ADA to large distortion-map misalignments beyond those covered by training augmentation | DCI attribute editing · Editing with large viewpoint changes | alignment quality | Hurt |
Closest papers by meaning
- Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · similarity 0.93)
- ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing (AAAI 2023 · similarity 0.93)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.91)
- Spatial-Contextual Discrepancy Information Compensation for GAN Inversion (AAAI 2024 · similarity 0.90)
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting (NeurIPS 2025 · similarity 0.89)
- The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · 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.