Research map / Image generation / Super-resolution
Image Super-Resolution by Neural Texture Transfer
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 multi-scale neural texture transfer from the reference (ablation) | SRNTT · CUFED5 HR (warp) | PSNR: 25.82 -> 33.87 | Helped |
| Replace feature swapping with optical flow (ablation) | SRNTT · CUFED5 HR (warp) | PSNR: 33.87 -> 25.82 | Hurt |
| Use all three VGG feature scales instead of a single scale (ablation) | SRNTT · CUFED5 HR (warp) | PSNR: 24.83 -> 33.87 | Helped |
| Use all three VGG feature scales instead of a single scale (ablation) | SRNTT · CUFED5 L1 | PSNR: 24.48 -> 25.42 | Helped |
| Add the weighted texture loss (ablation) | SRNTT · CUFED5 | PSNR: 25.25 -> 25.61 | Helped |
| Add adversarial and perceptual training instead of MSE-only training (ablation) | SRNTT · CUFED5 L1 | PSNR: 26.15 -> 25.42 | Hurt |
| Add adversarial and perceptual training instead of MSE-only training (ablation) | SRNTT · CUFED5 HR (warp) | PSNR: 29.29 -> 33.87 | Helped |
| Use optical flow instead of patch-based matching (ablation) | SRNTT · CUFED5 LR | PSNR: 25.10 -> 25.50 | Helped |
| Use external references with progressively lower similarity (ablation) | SRNTT · CUFED5 L1 to L4 | PSNR: 25.42 -> 25.23 | Hurt |
| Use SRNTT rather than MDSR | SRNTT · Sun80 | PSNR: 28.52 -> 27.59 | Hurt |
Closest papers by meaning
- Task Decoupled Framework for Reference-Based Super-Resolution (CVPR 2022 · similarity 0.93)
- Robust Reference-Based Super-Resolution via C2-Matching (CVPR 2021 · similarity 0.93)
- MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR 2021 · similarity 0.91)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.87)
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement (NeurIPS 2026 · similarity 0.87)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.86)
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.