Research map / Image generation / Super-resolution
Image Super-Resolution with Deep Dictionary
Shunta Maeda
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 batch normalization (ablation) | SRDD-64 · Set14 x4 | PSNR: 28.49 -> 28.54 | Improved |
| add bottleneck blocks and D_H code injection (ablation) | SRDD-64 · Set14 x4 | PSNR: 28.48 -> 28.54 | Improved |
| add compensation (ablation) | SRDD-64 · Set14 x4 | PSNR: 28.51 -> 28.54 | Improved |
| increase atoms from 64 to 128 (ablation) | SRDD · Set14 x4 in-domain | PSNR: 28.54 -> 28.65 | Improved |
| increase atoms from 64 to 128 | SRDD · Real-world historical images | NIQE: 5.877 -> 5.896 | Hurt |
| use SRDD-64 instead of CARN on OpenCV bicubic downsampled input | SRDD-64 · Set14 x4 | PSNR: 21.17 -> 21.52 | Improved |
| use SRDD-64 instead of CARN on OpenCV bilinear downsampled input | SRDD-64 · Set14 x4 | PSNR: 22.76 -> 23.13 | Improved |
| use SRDD-64 instead of CARN on OpenCV area downsampled input | SRDD-64 · Set14 x4 | PSNR: 26.74 -> 27.05 | Improved |
| use SRDD-64 instead of CARN | SRDD-64 · Real-world historical images | NIQE: 5.921 -> 5.877 | Improved |
| use ReLU instead of softmax for coefficients (ablation) | SRDD · training stability | stability | Hurt |
| use SRDD-64 instead of CARN in-domain | SRDD-64 · Set14 x4 (Matlab bicubic) | PSNR: 28.60 vs 28.54 | No clear effect |
Closest papers by meaning
- Deep Learning for Image Super-Resolution: A Survey (TPAMI 2020 · similarity 0.89)
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI 2016 · similarity 0.88)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.88)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.88)
- Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances (TPAMI 2023 · similarity 0.87)
- Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution (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.
