Research map / Image generation / Super-resolution
Learning Texture Transformer Network for 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 |
|---|---|---|---|
| Use TTSR-rec instead of SRNTT-rec | RefSR · CUFED5 testing set | PSNR: 26.24 -> 27.09 | Helped |
| Use TTSR-rec instead of RCAN | RefSR · Sun80 | PSNR: 29.86 -> 30.02 | Helped |
| Use TTSR-rec instead of MDSR | RefSR · Urban100 | PSNR: 25.51 -> 25.87 | Helped |
| Use TTSR-rec instead of RCAN | RefSR · Manga109 | PSNR: 29.38 -> 30.09 | Helped |
| Add hard-attention texture transfer (ablation) | Base · CUFED5 testing set | PSNR: 26.34 -> 26.59 | Helped |
| Add soft-attention feature synthesis (ablation) | Base+HA · CUFED5 testing set | PSNR: 26.59 -> 26.81 | Helped |
| Replace VGG19 features with learnable texture extractor (LTE) (ablation) | Base+HA+SA · CUFED5 testing set | PSNR: 26.81 -> 26.92 | Helped |
| Add cross-scale feature integration (CSFI) (ablation) | Base+TT · CUFED5 testing set | PSNR: +0.17 | Helped |
| Increase channels to 80 instead of adding CSFI (ablation) | Base+TT · CUFED5 testing set | PSNR: 26.92 -> 26.93 | No clear effect |
| Increase channels to 96 instead of adding CSFI (ablation) | Base+TT · CUFED5 testing set | PSNR: 26.92 -> 26.98 | Helped |
| Add transferal perceptual loss (ablation) | TTSR · CUFED5 testing set | PSNR: 25.20 -> 25.53 | Helped |
| Use the most relevant reference (L1) rather than the least relevant reference (L4) (ablation) | TTSR-rec · CUFED5 testing set | PSNR: 26.58 -> 26.99 | Helped |
Closest papers by meaning
- Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform (CVPR 2018 · similarity 0.91)
- Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss (CVPR 2024 · similarity 0.87)
- AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution (AAAI 2024 · similarity 0.87)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.87)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.87)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.87)
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.