Research map / Image generation / Super-resolution
Efficient Long-Range Attention Network for Image Super-Resolution
Xindong Zhang, Hui Zeng, Shi Guo, Lei Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 GMSA (multi-scale window attention) to ASA model (ablation) | ELAN-light · Urban100 x4 | PSNR (dB): 26.39 -> 26.60 | Improved |
| add GMSA (ablation) | ELAN-light · x4 | latency (ms): 66 -> 75 | Hurt |
| add accelerated self-attention (ASA) (ablation) | ELAN-light · x4 | latency (ms): 177 -> 66 | Improved |
| add shifted window mechanism (ablation) | ELAN-light · x4 | latency (ms): 247 -> 177 | Improved |
| add shifted window mechanism (ablation) | ELAN-light · Urban100 x4 | PSNR (dB): 26.40 -> 26.42 | No clear effect |
| add shared attention (n=1) (ablation) | ELAN-light · x4 | latency (ms): 75 -> 62 | Improved |
| add shared attention (n=1) (ablation) | ELAN-light · Urban100 x4 | PSNR (dB): 26.60 -> 26.54 | Hurt |
| increase shared attention depth from 1 to 5 (ablation) | ELAN-light · Urban100 x4 | PSNR (dB): 26.54 -> 26.35 | Hurt |
| increase shared attention depth from 1 to 5 (ablation) | ELAN-light · x4 | latency (ms): 62 -> 48 | Improved |
| replace SwinIR-light with ELAN-light | ELAN-light · x4 latency | latency (ms): 271 -> 62 | Improved |
| replace SwinIR with ELAN | ELAN · classic x4 Urban100 | PSNR (dB): 27.07 -> 27.13 | Improved |
| replace SwinIR with ELAN | ELAN · classic x2 latency | latency (ms): 2913 -> 1244 | Improved |
Closest papers by meaning
- Emulating Self-attention with Convolution for Efficient Image Super-Resolution (ICCV 2025 · similarity 0.92)
- Single Image Super-Resolution via a Holistic Attention Network (ECCV 2020 · similarity 0.90)
- DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution (ICCV 2023 · similarity 0.89)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.89)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.88)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · 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.
