Research map / Image generation / Super-resolution
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image 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 |
|---|---|---|---|
| Add LDL to RRDB | RRDB · DIV2K100 | LPIPS: 0.1099 -> 0.1011 | Helped |
| Add LDL to RRDB | RRDB · DIV2K100 | PSNR: 28.787 -> 28.951 | Helped |
| Add the primary artifact map M (ablation) | RRDB+LDL · DIV2K validation set | LPIPS: 0.1154 -> 0.1020 | Helped |
| Add the globally scaled artifact map σ·M (ablation) | RRDB+LDL with primary map · DIV2K validation set | LPIPS: 0.1020 -> 0.1006 | Helped |
| Replace the scaled map with refined map M_refine (ablation) | RRDB+LDL · DIV2K validation set | LPIPS: 0.1006 -> 0.1001 | Helped |
| Use the EMA model during testing with the refined map (ablation) | RRDB+LDL · DIV2K validation set | LPIPS: 0.1001 -> 0.0999 | Helped |
Closest papers by meaning
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.92)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.90)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.90)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.89)
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement (NeurIPS 2026 · similarity 0.89)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.89)
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.