Research map / Image generation / Super-resolution
Task Decoupled Framework for Reference-Based 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 |
|---|---|---|---|
| Separate super-resolution from reference texture transfer (ablation) | RefSR · CUFED5 | PSNR: 28.36 -> 28.64 | Helped |
| Separate super-resolution from reference texture transfer (ablation) | RefSR · Sun80 | PSNR: 30.01 -> 30.31 | Helped |
| Separate super-resolution from reference texture transfer (ablation) | RefSR · Urban100 | PSNR: 25.66 -> 26.71 | Helped |
| Separate super-resolution from reference texture transfer (ablation) | RefSR · Manga109 | PSNR: 29.98 -> 31.23 | Helped |
| Separate super-resolution from reference texture transfer (ablation) | RefSR · WR-SR | PSNR: 28.16 -> 28.52 | Helped |
| Add flow-based alignment (ablation) | SISR baseline for RefSR · CUFED5 | PSNR: 26.41 -> 27.91 | Helped |
| Add deformable convolution alignment (ablation) | SISR baseline for RefSR · CUFED5 | PSNR: 26.41 -> 28.29 | Helped |
| Combine flow-based and deformable alignment (ablation) | RefSR texture extraction · CUFED5 | PSNR: 27.91 -> 28.50; 28.29 -> 28.50 | Helped |
| Add adaptive texture transfer to combined alignments (ablation) | RefSR texture transfer · CUFED5 | PSNR: 28.50 -> 28.64 | Helped |
Closest papers by meaning
- Image Super-Resolution by Neural Texture Transfer (CVPR 2019 · similarity 0.93)
- Robust Reference-Based Super-Resolution via C2-Matching (CVPR 2021 · similarity 0.92)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.88)
- Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss (CVPR 2024 · similarity 0.86)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.86)
- Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach (CVPR 2025 · 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.