Research map / Image generation / Super-resolution
DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution
Xiang Li, Jiangxin Dong, Jinhui Tang, Jinshan Pan
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 |
|---|---|---|---|
| use both MHDLSA and SparseGSA in the HDTB instead of only MHDLSA (ablation) | DLGSANet · Urban100 x4 | PSNR (dB): 26.88 -> 27.17 | Improved |
| use both MHDLSA and SparseGSA in the HDTB instead of only SparseGSA (ablation) | DLGSANet · Urban100 x4 | PSNR (dB): 26.86 -> 27.17 | Improved |
| replace softmax with ReLU in global self-attention (SparseGSA) (ablation) | DLGSANet · Urban100 x4 | PSNR (dB): 27.05 -> 27.17 | Improved |
| replace window multi-head attention with dynamic local self-attention (MHDLSA) (ablation) | DLGSANet · Urban100 x4 | PSNR (dB): 26.89 -> 27.17 | Improved |
| use DLGSANet instead of ELAN at x2 on Urban100 | classical SR · Urban100 x2 | PSNR (dB): 33.44 -> 33.41 | No clear effect |
| DLGSANet versus ELAN on parameters and FLOPs at x4 | classical SR · x4 classical SR | FLOPs (G): 494 -> 274 | Improved |
| DLGSANet-light versus ELAN-light on Manga109 x4 | lightweight SR · Manga109 x4 | PSNR (dB): 30.92 -> 31.13 | Improved |
| DLGSANet versus transformer SR models on running time | classical SR · x4 running time | Running time (ms): 278 -> 187 | Improved |
| lightweight CNN IMDN is faster than DLGSANet-tiny | lightweight SR · x4 running time | Running time (ms): 8 vs 38 | Hurt |
Closest papers by meaning
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.91)
- Adaptive Sparse Self-Attention for Efficient Image Super-Resolution and Beyond (TPAMI 2026 · similarity 0.91)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.89)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.88)
- Progressive Focused Transformer for Single Image Super-Resolution (CVPR 2025 · similarity 0.87)
- CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution (CVPR 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.
