Research map / Image generation / GANs
Interpreting the Latent Space of GANs for Semantic Face 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 linear attribute boundaries in latent space to edit facial attributes | PGGAN · Synthesized faces | qualitative attribute controllability | Helped |
| Project the editing direction to remove its component along a conditioned attribute | InterFaceGAN · Synthesized faces with correlated attributes | independence of attribute editing | Helped |
| Use StyleGAN W space rather than Z space for attribute editing | StyleGAN · Face attribute editing, especially long-distance manipulation | qualitative editing quality | Helped |
| Use conditional projection to decorrelate attributes in Z space | StyleGAN · Age and eyeglasses editing | qualitative editing quality | Helped |
| Use an encoder trained together with the generator instead of a separately learned inversion encoder | Encoder-decoder generative model · Real face editing | reconstruction and manipulation quality | Helped |
| Move the latent code too far from the semantic boundary | InterFaceGAN · Synthesized faces | preservation of original identity | Hurt |
| Invert real images into PGGAN latent codes | PGGAN with optimization-based or encoder-based inversion · Real face editing | inversion and reconstruction quality | Hurt |
Closest papers by meaning
- Navigating the GAN Parameter Space for Semantic Image Editing (CVPR 2021 · similarity 0.91)
- Closed-Form Factorization of Latent Semantics in GANs (CVPR 2021 · similarity 0.91)
- FEditNet: Few-Shot Editing of Latent Semantics in GAN Spaces (AAAI 2023 · similarity 0.91)
- Surrogate Gradient Field for Latent Space Manipulation (CVPR 2021 · similarity 0.91)
- L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute Editing (CVPR 2021 · similarity 0.91)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · similarity 0.89)
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.