Research map / Image generation / Super-resolution
SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution
mingjun zheng, Long Sun, Jiangxin Dong, 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 |
|---|---|---|---|
| add SMFA module (ablation) | SMFANet · Urban100 x4 | PSNR: 25.54 -> 26.19 | Improved |
| add EASA branch (ablation) | SMFANet · Urban100 x4 | PSNR: 25.94 -> 26.19 | Improved |
| add LDE branch (ablation) | SMFANet · Urban100 x4 | PSNR: 25.92 -> 26.19 | Improved |
| replace EASA with window-based self-attention (ablation) | SMFANet · Urban100 x4 | PSNR: 26.19 -> 26.20 | No clear effect |
| replace EASA with window-based SA (efficiency) (ablation) | SMFANet · x4 SR | GPU memory (M): 93.20 -> 269.69 | Hurt |
| use parallel EASA and LDE branches instead of dual LDE or dual EASA (ablation) | SMFANet · Urban100 x4 | PSNR: 26.02 / 25.94 -> 26.19 | Improved |
| run EASA and LDE in parallel rather than sequentially (ablation) | SMFANet · Urban100 x4 | PSNR: 26.04 -> 26.19 | Improved |
| add variance modulation sigma^2(X) in EASA (ablation) | SMFANet · Urban100 x4 | PSNR: 26.13 -> 26.19 | Improved |
| use addition instead of element-wise product for variance modulation (ablation) | SMFANet · Urban100 x4 | PSNR: 26.14 -> 26.19 | Improved |
| add PCFN (ablation) | SMFANet · Urban100 x4 | PSNR: 25.89 -> 26.19 | Improved |
| replace PCFN with GDFN (ablation) | SMFANet · Urban100 x4 | PSNR: 26.19 -> 26.22 | No clear effect |
| train on DF2K instead of DIV2K | SMFANet · Manga109 x4 | PSNR: 30.72 -> 30.82 | Improved |
Later papers that compared with this method
1 later accepted paper reports SMFANet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution (CVPR 2026 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Adaptive Sparse Self-Attention for Efficient Image Super-Resolution and Beyond (TPAMI 2026 · similarity 0.91)
- DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution (ICCV 2023 · similarity 0.90)
- Emulating Self-attention with Convolution for Efficient Image Super-Resolution (ICCV 2025 · similarity 0.89)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.88)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.87)
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration (CVPR 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.
