Research map / Image generation / Super-resolution
Metric Learning Based Interactive Modulation for Real-World Super-Resolution
Chong Mou, Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang, Ying Shan
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 |
|---|---|---|---|
| use MM-RealSR with metric-learning modulation instead of CUGAN's best of 121 traversed settings | MM-RealSR · RealSRSet | LPIPS: 0.3757 -> 0.3606 | Improved |
| use MM-RealSR instead of CUGAN | MM-RealSR · AIM19 | LPIPS: 0.4635 -> 0.3948 | Improved |
| add interactive modulation to Real-ESRGAN upper bound | MM-RealSR · RealSRSet | LPIPS: 0.3640 -> 0.3606 | Improved |
| add interactive modulation to Real-ESRGAN upper bound | MM-RealSR · RealSRSet | DISTS: 0.1545 -> 0.1664 | Hurt |
| add interactive modulation to Real-ESRGAN upper bound | MM-RealSR · AIM19 | NIQE: 3.60 -> 3.61 | No clear effect |
| use one modulated model instead of four segment-trained models with best-of-four selection | MM-RealSR · RealSRSet | LPIPS: 0.3905 -> 0.3662 | Improved |
| use one modulated model instead of four segment-trained models with best-of-four selection | MM-RealSR · RealSRSet | DISTS: 0.1760 -> 0.1632 | Improved |
| add anchor loss to metric learning (ablation) | UDEM · UDEM score range on synthetic degradations | degradation score dynamic range | Improved |
Closest papers by meaning
- Empowering Real-World Image Super-Resolution With Flexible Interactive Modulation (TPAMI 2024 · similarity 0.96)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.87)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 2025 · similarity 0.87)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.87)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.86)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · 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.
