Research map / Image generation / Super-resolution
Single Image Super-Resolution via a Holistic Attention Network
Ben Niu, Weilei Wen, Wenqi Ren, Xiangde Zhang, Lianping Yang, Shuzhen Wang, Kaihao Zhang, Xiaochun Cao, Haifeng Shen
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 LAM and CSAM to the RCAN-style baseline (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.22 -> 31.42 | Improved |
| add LAM alone to the baseline (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.22 -> 31.38 | Improved |
| add CSAM alone to the baseline (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.22 -> 31.28 | Improved |
| add CSAM on top of LAM (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.38 -> 31.42 | Improved |
| add LAM on top of CSAM (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.28 -> 31.42 | Improved |
| feed 3 residual groups to LAM instead of RCAN without LAM (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.22 -> 31.40 | Improved |
| increase residual groups fed to LAM from 3 to 10 (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.40 -> 31.42 | Improved |
| increase CSAMs from 1 to 3 (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.42 -> 31.46 | Improved |
| increase CSAMs from 3 to 10 (ablation) | HAN · Manga109 x4 (BI) | PSNR: 31.46 -> 31.43 | No clear effect |
| replace SAN attention with HAN on same RCAN backbone | HAN · Urban100 x4 (BI) | PSNR: 26.79 -> 26.85 | Improved |
| replace SAN with HAN at 8x scale | HAN · Set5 x8 (BI) | PSNR: 27.22 -> 27.33 | Improved |
| replace RCAN with HAN at 8x scale | HAN · Urban100 x8 (BI) | PSNR: 23.00 -> 22.98 | No clear effect |
Closest papers by meaning
- Second-Order Attention Network for Single Image Super-Resolution (CVPR 2019 · similarity 0.91)
- Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution (ICCV 2021 · similarity 0.91)
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks (ECCV 2018 · similarity 0.91)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.89)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.88)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.88)
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.
