Research map / Image generation / Editing and style transfer
STGAN: A Unified Selective Transfer Network for Arbitrary 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 |
|---|---|---|---|
| Use the difference between target and source attributes rather than the full target attribute vector (ablation) | STGAN · CelebA facial attribute editing | attribute generation accuracy | Helped |
| Use the difference attribute vector rather than the full target attribute vector (ablation) | STGAN · CelebA reconstruction | reconstruction quality | Helped |
| Replace STU with a convolution conditioned on encoder features and the difference attribute vector (ablation) | STGAN · CelebA facial attribute editing | attribute generation accuracy | Hurt |
| Use residual learning for the convolution-based feature transformation (ablation) | STGAN-conv · CelebA facial attribute editing | attribute generation accuracy | Helped |
| Use residual learning for STU (ablation) | STGAN · CelebA facial attribute editing | attribute generation accuracy | Mixed |
| Use the transformed feature as the hidden state, replacing STU's modified output arrangement with GRU (ablation) | STGAN · CelebA facial attribute editing | attribute generation accuracy | Mixed |
| Add skip connections (ablation) | AttGAN · AttGAN attribute editing | attribute generation accuracy | Mixed |
Closest papers by meaning
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · similarity 0.89)
- L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute Editing (CVPR 2021 · similarity 0.89)
- Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation (ICLR 2021 · similarity 0.88)
- Mask-Guided Portrait Editing With Conditional GANs (CVPR 2019 · similarity 0.88)
- The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · similarity 0.85)
- Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · similarity 0.85)
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.