Research map / Image generation / GANs
Generative Attribute Controller With Conditional Filtered Generative Adversarial Networks
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 |
|---|---|---|---|
| replace the CGAN's direct attribute input with a filtered, multidimensional attribute latent variable | CGAN · MNIST, CUB, and CelebA | attribute controllability | Helped |
| use a categorical radio-button controller (ablation) | CFGAN · MNIST and CelebA | categorical attribute control | Helped |
| use a continuous slide-bar controller centered on the non-attribute state (ablation) | CFGAN · MNIST and CelebA | continuous attribute control | Helped |
| use a continuous slide-bar controller with attribute and non-attribute states in opposite fields (ablation) | CFGAN · MNIST and CelebA | continuous attribute control | Helped |
| condition the controllable latent variable on the attribute using a filtering architecture | InfoCGAN · CelebA glasses generation | attribute-specific variation | Helped |
| use CFGAN rather than CGAN for editing while preserving identity | CelebA face editing · CelebA | identity retention | No clear effect |
| exchange the attribute-dependent latent variable between a target and reference image | CFGAN · CelebA attribute transfer | attribute transfer | Helped |
| retrieve images using the attribute-dependent latent variable rather than image pixels or identity latent | CFGAN · CelebA attribute-based retrieval | attribute retrieval relevance | Helped |
Closest papers by meaning
- Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons (AAAI 2020 · similarity 0.88)
- Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation (ICLR 2021 · similarity 0.87)
- Attribute Group Editing for Reliable Few-Shot Image Generation (CVPR 2022 · similarity 0.87)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.87)
- Cluster-Guided Image Synthesis With Unconditional Models (CVPR 2022 · similarity 0.86)
- SDGAN: Disentangling Semantic Manipulation for Facial 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.