Research map / Image generation / Super-resolution
RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution
Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao
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 a Ranker with rank-content loss to SRGAN | SRGAN · PIRM-Test | NIQE: 2.71 -> 2.51 | Improved |
| add a Ranker with rank-content loss to SRGAN | SRGAN · BSD100 | NIQE: 3.29 -> 3.01 | Improved |
| add a Ranker with rank-content loss to ESRGAN-level baseline comparison | ESRGAN · Set14 | NIQE: 3.28 -> 3.28 | No clear effect |
| train Ranker with ground-truth HR as third algorithm instead of ESRGAN (ablation) | RankSRGAN · PIRM-Test | PSNR: 25.60 -> 26.00 | Improved |
| train Ranker with ground-truth HR as third algorithm instead of ESRGAN (ablation) | RankSRGAN · PIRM-Test | NIQE: 2.51 -> 2.58 | Hurt |
| use Ma-based Ranker instead of NIQE-based Ranker (ablation) | RankSRGAN · PIRM-Test | NIQE: 2.51 -> 2.65 | Hurt |
| use Ma-based Ranker instead of NIQE-based Ranker (ablation) | RankSRGAN · PIRM-Test | 10-Ma: 1.39 -> 1.38 | Improved |
| use PI-based Ranker instead of NIQE-based Ranker (ablation) | RankSRGAN · PIRM-Test | PI: 1.95 -> 1.94 | Improved |
| use margin-ranking Ranker instead of regression Ranker (NIQE labels) (ablation) | RankSRGAN · PIRM-Test | NIQE: 2.53 -> 2.51 | Improved |
| use margin-ranking Ranker instead of regression Ranker (Ma labels) (ablation) | RankSRGAN · PIRM-Test | 10-Ma: 1.43 -> 1.38 | Improved |
| use margin-ranking Ranker instead of regression Ranker (Ma labels) (ablation) | RankSRGAN · PIRM-Test | NIQE: 2.61 -> 2.65 | Hurt |
| label rank dataset by metric rank instead of model classification (ablation) | RankSRGAN · PIRM-Test | NIQE | Improved |
Closest papers by meaning
- RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank (TPAMI 2021 · similarity 0.99)
- Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions (ICLR 2023 · similarity 0.89)
- SRFeat: Single Image Super-Resolution with Feature Discrimination (ECCV 2018 · similarity 0.89)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.87)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.86)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 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.
