Research map / Image generation / Editing and style transfer
EditGAN: High-Precision Semantic Image Editing
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 segmentation-guided EditGAN instead of MaskGAN | Smile editing · Smile edit benchmark (400 images) | Attribute accuracy (%): 77.3 -> 91.5 | Helped |
| Use segmentation-guided EditGAN instead of InterFaceGAN | Smile editing · Smile edit benchmark (400 images) | ID score: 0.7295 -> 0.7047 | Hurt |
| Add 30 self-supervised refinement steps (ablation) | EditGAN smile edit · Smile edit benchmark (400 images) | ID score: 0.7047 -> 0.7452 | Helped |
| Add 30 self-supervised refinement steps (ablation) | EditGAN smile edit · Smile edit benchmark (400 images) | Attribute accuracy (%): 91.5 -> 85.8 | Hurt |
| Add 30 self-supervised refinement steps (ablation) | EditGAN smile edit · Smile edit benchmark (400 images) | FID: 41.74 -> 40.83 | Helped |
| Use Encoding4Editing encoder in LocalEditing | LocalEditing · Smile edit benchmark (400 images) | Attribute accuracy (%): 26.0 -> 41.75 | Helped |
| Use Encoding4Editing encoder in LocalEditing | LocalEditing · Smile edit benchmark (400 images) | FID: 41.26 -> 48.28 | Hurt |
| Increase editing-vector scale (ablation) | EditGAN · Smile edit benchmark | FID | Hurt |
| Add self-supervised refinement to editing-vector application (ablation) | EditGAN · Smile edit benchmark | FID | Helped |
| Add more than 30 refinement steps (ablation) | EditGAN · Smile edit benchmark | editing performance | No clear effect |
Closest papers by meaning
- Editing in Style: Uncovering the Local Semantics of GANs (CVPR 2020 · similarity 0.93)
- Navigating the GAN Parameter Space for Semantic Image Editing (CVPR 2021 · similarity 0.92)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.90)
- Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · similarity 0.88)
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.88)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 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.