Research map / Image generation / Super-resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
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 adversarial perceptual-loss SRGAN-VGG54 instead of SRResNet-MSE | SR image reconstruction · Set5 | MOS: 3.37 -> 3.58 | Helped |
| Use the adversarial perceptual-loss SRGAN-VGG54 instead of SRResNet-MSE | SR image reconstruction · Set14 | MOS: 2.98 -> 3.72 | Helped |
| Use the adversarial perceptual-loss SRGAN-VGG54 instead of SRResNet-MSE | SR image reconstruction · BSD100 | MOS: 2.29 -> 3.56 | Helped |
| Use adversarial perceptual loss rather than MSE-only training | SR image reconstruction · Set5 | PSNR (dB): 32.05 -> 29.40 | Hurt |
| Use adversarial perceptual loss rather than MSE-only training | SR image reconstruction · Set14 | PSNR (dB): 28.49 -> 26.02 | Hurt |
| Use adversarial perceptual loss rather than MSE-only training | SR image reconstruction · BSD100 | PSNR (dB): 27.58 -> 25.16 | Hurt |
| Add adversarial loss to SRResNet-VGG22 training (ablation) | VGG22 content-loss SR · Set5 | MOS: 3.46 -> 3.78 | Helped |
| Add adversarial loss to SRResNet-VGG22 training (ablation) | VGG22 content-loss SR · Set14 | MOS: 3.15 -> 3.57 | Helped |
| Replace VGG22 content loss with deeper VGG54 content loss (ablation) | SRGAN · Set5 | MOS: 3.78 -> 3.58 | Hurt |
| Replace VGG22 content loss with deeper VGG54 content loss (ablation) | SRGAN · Set14 | MOS: 3.57 -> 3.72 | Helped |
Closest papers by meaning
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.91)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.90)
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement (NeurIPS 2026 · similarity 0.90)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.89)
- Adversarial Diffusion Compression for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.89)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.89)
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.