Research map / Image generation / Super-resolution
Residual Dense Network for Image Super-Resolution
Read the paperCheck 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 contiguous memory (CM) (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.89 | Helped |
| add local residual learning (LRL) (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.92 | Helped |
| add global feature fusion (GFF) (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.78 | Helped |
| add CM and LRL (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.99 | Helped |
| add CM and GFF (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.98 | Helped |
| add LRL and GFF (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 37.97 | Helped |
| use CM, LRL, and GFF together (ablation) | RDN · Set5 ×2 BI, 200 epochs | PSNR: 34.87 -> 38.06 | Helped |
| increase the number of RDBs, layers per RDB, or growth rate (ablation) | RDN · Set5 ×2 BI | PSNR | Helped |
| apply self-ensemble inference | RDN · BI degradation benchmarks | PSNR | Helped |
| use RDN rather than competing methods | Image SR models · BI degradation, ×2 | PSNR | Helped |
| use RDN rather than competing methods | Image SR models · BI degradation, ×3 and ×4 | PSNR | Mixed |
| use RDN rather than competing methods | Image SR models · BD and DN degradation, ×3 | PSNR | Helped |
Closest papers by meaning
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.89)
- OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution (AAAI 2024 · similarity 0.89)
- Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution (AAAI 2023 · similarity 0.88)
- Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining (CVPR 2020 · similarity 0.88)
- Deeply-Recursive Convolutional Network for Image Super-Resolution (CVPR 2016 · similarity 0.88)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 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.