Research map / Image generation / Super-resolution
Explorable Super Resolution
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 |
|---|---|---|---|
| Wrap EDSR with the consistency enforcing module | EDSR · BSD100, 2× SR | PSNR: 35.97 -> 36.11 | Helped |
| Wrap EDSR with the consistency enforcing module | EDSR · BSD100, 3× SR | PSNR: 32.27 -> 32.36 | Helped |
| Wrap EDSR with the consistency enforcing module | EDSR · BSD100, 4× SR | PSNR: 30.30 -> 30.37 | Helped |
| Add control signal z while retaining the ESRGAN loss (ablation) | ESRGAN · BSD100 test set, 4× SR | diversity (σ): $0$ -> $3.6\pm1.7$ | Helped |
| Add control signal z while retaining the ESRGAN loss (ablation) | ESRGAN · BSD100 test set, 4× SR | NIQE: $3.5\pm0.9$ -> $3.7\pm0.8$ | No clear effect |
| Remove full-reference reconstruction losses while keeping the control signal (ablation) | ESRGAN with z · BSD100 test set, 4× SR | diversity (σ): $3.6\pm1.7$ -> $7.2\pm3.4$ | Helped |
| Remove full-reference reconstruction losses while keeping the control signal (ablation) | ESRGAN with z · BSD100 test set, 4× SR | NIQE: $3.7\pm0.8$ -> $3.7\pm0.9$ | No clear effect |
| Use the L_Map loss to train the control-to-image mapping (ablation) | Explorable SR · Image-pattern generation examples | plausibility of generated patterns | Helped |
Closest papers by meaning
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.90)
- Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation (CVPR 2021 · similarity 0.90)
- Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution (CVPR 2024 · similarity 0.89)
- Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR 2025 · similarity 0.88)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 2025 · similarity 0.88)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.88)
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.