Research map / Image generation / GANs
RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
Hongyu Ren, Diqi Chen, Yizhou Wang
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 perceptual loss to the restorator (ablation) | RAN · TID2013 | SROCC: 0.893 -> 0.948 | Improved |
| add perceptual loss to the restorator (ablation) | RAN · TID2013 | PLCC: 0.879 -> 0.937 | Improved |
| use Wasserstein adversarial loss instead of logarithm-based adversarial loss (ablation) | RAN · TID2013 | SROCC: 0.936 -> 0.948 | Improved |
| use Wasserstein adversarial loss instead of logarithm-based adversarial loss (ablation) | RAN · TID2013 | PLCC: 0.906 -> 0.937 | Improved |
| add a discriminator to the restorator (ablation) | RAN · TID2013 | SROCC: 0.854 -> 0.948 | Improved |
| add a discriminator to the restorator (ablation) | RAN · TID2013 | PLCC: 0.856 -> 0.937 | Improved |
| use weighted patch aggregation instead of averaging patch scores (ablation) | RAN · TID2013 | SROCC: 0.857 -> 0.948 | Improved |
| use weighted patch aggregation instead of averaging patch scores (ablation) | RAN · TID2013 | PLCC: 0.884 -> 0.937 | Improved |
| use RAN rather than DNN | NR-IQA evaluation · TID2013 | SROCC: 0.933 -> 0.948 | Improved |
| use RAN rather than DNN | NR-IQA evaluation · TID2013 | PLCC: 0.909 -> 0.937 | Improved |
| use RAN rather than DNN | NR-IQA evaluation · LIVE | SROCC: 0.960 -> 0.972 | Improved |
| use RAN rather than DNN | NR-IQA evaluation · LIVE | PLCC: 0.972 -> 0.968 | Hurt |
Closest papers by meaning
- Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning (CVPR 2018 · similarity 0.89)
- Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity (ICML 2024 · similarity 0.87)
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement (CVPR 2026 · similarity 0.86)
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered (NeurIPS 2026 · similarity 0.85)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.85)
- Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization (CVPR 2024 · similarity 0.85)
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.
