Research map / Image generation / GANs
Adversarial Generation of Continuous Images
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 |
|---|---|---|---|
| add FMM activation (ablation) | INR-GAN · Churches | FID: 10.35 -> 7.12 | Helped |
| add FMM activation (ablation) | INR-GAN · Bedrooms | FID: 11.73 -> 6.27 | Helped |
| incorporate StyleGAN2's architecture (ablation) | INR-GAN · Churches | FID: 7.12 -> 5.09 | Helped |
| incorporate StyleGAN2's architecture (ablation) | INR-GAN · Bedrooms | FID: 6.27 -> 4.96 | Helped |
| add bilinear upsampling to the StyleGAN2-architecture INR-GAN (ablation) | INR-GAN · Churches | FID: 5.09 -> 3.12 | Helped |
| add bilinear upsampling to the StyleGAN2-architecture INR-GAN (ablation) | INR-GAN · Bedrooms | FID: 4.96 -> 3.41 | Helped |
| replace the basic INR decoder with a hypernetwork-based decoder (ablation) | Basic INR decoder · MiniImageNet | FID: 271.5 -> 112.9 | Helped |
| add Fourier embeddings (ablation) | Hypernetwork-based decoder · MiniImageNet | FID: 112.9 -> 102.8 | Helped |
| add FMM (ablation) | Hypernetwork decoder with Fourier embeddings · LSUN-10 | FID | Helped |
| add FMM (ablation) | Hypernetwork decoder with Fourier embeddings · MiniImageNet | FID: 102.8 -> 84.66 | Helped |
| add multi-scale INR (ablation) | Hypernetwork decoder with Fourier embeddings and FMM · LSUN-10 | FID: 23.78 -> 12.47 | Helped |
| add multi-scale INR (ablation) | Hypernetwork decoder with Fourier embeddings and FMM · MiniImageNet | FID: 84.66 -> 59.63 | Helped |
Closest papers by meaning
- Adversarial Text to Continuous Image Generation (CVPR 2024 · similarity 0.89)
- Polynomial Implicit Neural Representations for Large Diverse Datasets (CVPR 2023 · similarity 0.88)
- Image Processing Using Multi-Code GAN Prior (CVPR 2020 · similarity 0.87)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis (ICLR 2019 · similarity 0.87)
- Adversarial Diffusion Compression for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.87)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.86)
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.