Research map / Image generation / Super-resolution
Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination
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 |
|---|---|---|---|
| Add naturalness and adversarial losses to the reconstruction-only FRSR objective (ablation) | FRSR, producing NatSR · BSD100 | NMD score: 0.044 ± 0.011 -> 1.000 ± 0.000 | Helped |
| Add naturalness and adversarial losses to the reconstruction-only FRSR objective (ablation) | FRSR, producing NatSR · Set5 ×4 | PSNR: 32.20 -> 30.98 | Hurt |
| Add naturalness and adversarial losses to the reconstruction-only FRSR objective (ablation) | FRSR, producing NatSR · Set14 ×4 | PSNR: 28.54 -> 27.42 | Hurt |
| Add naturalness and adversarial losses to the reconstruction-only FRSR objective (ablation) | FRSR, producing NatSR · BSD100 ×4 | PSNR: 27.60 -> 26.44 | Hurt |
| Add naturalness and adversarial losses to the reconstruction-only FRSR objective (ablation) | FRSR, producing NatSR · Urban100 ×4 | PSNR: 26.21 -> 25.46 | Hurt |
| Constrain the generator with the natural manifold discriminator | NatSR · BSD100 | RGB-PSNR (dB), LR-domain consistency: 36.16 -> 45.94 | Helped |
Closest papers by meaning
- Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation (CVPR 2023 · similarity 0.91)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.88)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.88)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.88)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.87)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.87)
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.