Research map / Architectures and efficiency / Attention and transformers
Image Super-Resolution With Non-Local Sparse Attention
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 NLSA modules to the EDSR backbone | EDSR · Urban100 ×4 | PSNR: 26.64 -> 26.96 | Helped |
| Add NLSA modules to the EDSR backbone | EDSR · Manga109 ×4 | PSNR: 31.02 -> 31.27 | Helped |
| Use spherical LSH partitioning instead of no attention (ablation) | Set5 ×2 baseline · Set5 ×2 | PSNR: 37.78 -> 37.92 | Helped |
| Use random hashing instead of spherical LSH (ablation) | NLSA · Set5 ×2 | PSNR: 37.92 -> 37.79 | Hurt |
| Use local window partitioning instead of spherical LSH (ablation) | NLSA · Set5 ×2 | PSNR: 37.92 -> 37.83 | Hurt |
| Increase attention rounds from 1 to 8 (ablation) | NLSA · Set5 ×2 | PSNR: 37.87 -> 37.93 | Helped |
| Share the linear projections (θ = φ) (ablation) | Non-Local Attention · Set5 ×2 | PSNR: 37.86 -> 37.87 | No clear effect |
| Increase attention rounds from 1 to 8 (ablation) | NLSA · Set5 ×2 GFLOPs | GFLOPs: 0.9 -> 4.3 | Hurt |
Closest papers by meaning
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.87)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.86)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution (CVPR 2024 · similarity 0.86)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 2024 · similarity 0.86)
- CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution (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.