Research map / Image generation / Super-resolution
Image-Adaptive GAN Based Reconstruction
Shady Abu Hussein, Tom Tirer, Raja Giryes
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 image-adaptive joint optimization of generator weights and latent (IAGAN vs CSGM) (ablation) | CSGM · CelebA-HQ CS ratio 0.5 noise | PSNR (dB): 21.82 -> 28.26 | Improved |
| add image-adaptive optimization (ablation) | CSGM · CelebA CS ratio 0.5 | perceptual similarity (PS): 0.241 -> 0.066 | Improved |
| add image-adaptive optimization (ablation) | CSGM · CelebA SR x4 no noise | PSNR (dB): 20.51 -> 27.16 | Improved |
| add back-projection post-processing to CSGM (ablation) | CSGM · CelebA SR x4 no noise | PSNR (dB): 20.51 -> 26.44 | Improved |
| add back-projection to IAGAN (ablation) | IAGAN · CelebA SR x4 no noise | PSNR (dB): 27.16 -> 27.14 | No clear effect |
| add back-projection to IAGAN (ablation) | IAGAN · CelebA-HQ SR x8 no noise | perceptual similarity (PS): 0.387 -> 0.360 | Improved |
| IAGAN vs DIP on CelebA | IAGAN · CelebA CS ratio 0.3 noise | PSNR (dB): 25.96 -> 25.50 | Mixed |
Closest papers by meaning
- Learning to Super-Resolve Blurry Face and Text Images (ICCV 2017 · similarity 0.89)
- To learn image super-resolution, use a GAN to learn how to do image degradation first (ECCV 2018 · similarity 0.88)
- Invertible generative models for inverse problems: mitigating representation error and dataset bias (ICML 2020 · similarity 0.88)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.87)
- pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization (NeurIPS 2024 · similarity 0.86)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 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.
