Research map / Image generation / Super-resolution
Meta-Transfer Learning for Zero-Shot 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 |
|---|---|---|---|
| Use 10 rather than 1 meta-test gradient update (ablation) | MZSR · Set5, ×2 bicubic | PSNR: 36.77 -> 37.25 | Helped |
| Use 10 rather than 1 meta-test gradient update (ablation) | MZSR · Set5, ×2, gᵈ₂.₀ | PSNR: 35.20 -> 36.05 | Helped |
| Use 10 rather than 1 meta-test gradient update (ablation) | MZSR · Set5, ×2, gᵈ₀.₂ | PSNR: 33.14 -> 33.74 | Helped |
| Use 10 rather than 1 meta-test gradient update (ablation) | MZSR · Urban100, ×2, gᵈani | PSNR: 26.51 -> 27.34 | Helped |
| Train one model across scaling factors ×2 and ×4 instead of a single-scale model (ablation) | MZSR · Set5, ×2, gᵈ₀.₂ | PSNR: (-0.41) | Hurt |
| Train one model across scaling factors ×2 and ×4 instead of a single-scale model (ablation) | MZSR · Set5, ×2, gᵈ₂.₀ | PSNR: (-0.97) | Hurt |
| Train one model across scaling factors ×2 and ×4 instead of a single-scale model (ablation) | MZSR · Set5, ×2, gᵈani | PSNR: (-0.83) | Hurt |
| Provide a mismatched blur kernel at meta-test time (ablation) | MZSR · ×4, gᵈ₂.₀ | PSNR: 24.32 dB; 30.31 dB with the true kernel | Hurt |
Closest papers by meaning
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.86)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.86)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.85)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.85)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.85)
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.