Research map / Image generation / Editing and style transfer
PetsGAN: Rethinking Priors for Single Image Generation
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 joint rather than cascaded training (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | SIFID: 0.10 -> 0.08; 0.11 -> 0.09; 0.50 -> 0.21 | Helped |
| Use joint rather than cascaded training (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | LPIPS: 0.31 -> 0.31; 0.34 -> 0.33; 0.37 -> 0.35 | Mixed |
| Add patch adversarial loss (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | SIFID: 0.23 -> 0.08; 0.23 -> 0.09; 0.30 -> 0.21 | Helped |
| Add patch adversarial loss (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | LPIPS: 0.33 -> 0.31; 0.38 -> 0.33; 0.39 -> 0.35 | Mixed |
| Add external prior (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | LPIPS: 0.18 -> 0.31; 0.21 -> 0.33; 0.22 -> 0.35 | Helped |
| Add external prior (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | SIFID: 0.11 -> 0.08; 0.11 -> 0.09; 0.25 -> 0.21 | Helped |
| Add internal prior (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | SIFID: 0.20 -> 0.08; 0.19 -> 0.09; 0.40 -> 0.21 | Helped |
| Add internal prior (ablation) | PetsGAN · Places50, LSUN50, ImageNet50 | LPIPS: 0.23 -> 0.31; 0.26 -> 0.33; 0.33 -> 0.35 | Helped |
Closest papers by meaning
- Drop the GAN: In Defense of Patches Nearest Neighbors As Single Image Generative Models (CVPR 2022 · similarity 0.92)
- Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation (ICLR 2019 · similarity 0.89)
- Instance-Conditioned GAN (NeurIPS 2021 · similarity 0.88)
- WeditGAN: Few-Shot Image Generation via Latent Space Relocation (AAAI 2024 · similarity 0.88)
- Image Inpainting via Iteratively Decoupled Probabilistic Modeling (ICLR 2024 · similarity 0.87)
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (AAAI 2024 · similarity 0.87)
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.