Research map / Image generation / Super-resolution
Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation
Read the paperCheck 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 |
|---|---|---|---|
| Estimate and apply locally varying objective maps rather than use FxSR's single objective setting | SROOE · BSD100 | LPIPS: 0.1572 -> 0.1500 | Helped |
| Estimate and apply locally varying objective maps rather than use FxSR's single objective setting | SROOE · Urban100 | PSNR: 24.08 -> 24.33 | Helped |
| Estimate and apply locally varying objective maps rather than use FxSR's single objective setting | SROOE · Manga109 | LPIPS: 0.0580 -> 0.0524 | Helped |
| Use trajectory P1234 instead of P2 (ablation) | SROOE · Five-benchmark average | LPIPS: 0.1000 -> 0.0978 | Helped |
| Estimate a local objective map instead of using fixed t (ablation) | SROOE-P2 · Five-benchmark average | LPIPS: 0.1011 -> 0.1000 | Helped |
| Train on DF2K rather than DIV2K (ablation) | SROOE-P1234 · Five-benchmark average | PSNR: 26.65 -> 26.74 | Helped |
| Use the searched per-pixel optimal map T*S instead of the estimated map (ablation) | SROOE · Five-benchmark average | LPIPS: 0.0960 -> 0.0875 | Helped |
Closest papers by meaning
- Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR 2025 · similarity 0.90)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.89)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.89)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.88)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.88)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · 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.