Research map / Image generation / Super-resolution
Joint Sub-bands Learning with Clique Structures for Wavelet Domain 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 |
|---|---|---|---|
| Use SRCliqueNet instead of EDSR | Single-image super-resolution · Set5 2× | PSNR: 38.23 vs 38.11 | Helped |
| Use SRCliqueNet instead of EDSR | Single-image super-resolution · Set14 2× | PSNR: 33.96 vs 33.92 | Helped |
| Use SRCliqueNet instead of EDSR | Single-image super-resolution · BSDS100 2× | PSNR: 32.36 vs 32.32 | Helped |
| Use SRCliqueNet instead of EDSR | Single-image super-resolution · Urban100 2× | PSNR: 32.86 vs 32.93 | Hurt |
| Use SRCliqueNet instead of D-DBPN | Single-image super-resolution · Set5 4× | PSNR: 32.61 vs 32.47 | Helped |
| Use SRCliqueNet instead of D-DBPN | Single-image super-resolution · Set14 4× | PSNR: 28.88 vs 28.82 | Helped |
| Use SRCliqueNet instead of D-DBPN | Single-image super-resolution · BSDS100 4× | PSNR: 27.77 vs 27.72 | Helped |
| Use SRCliqueNet instead of EDSR | Single-image super-resolution · Urban100 4× | PSNR: 26.69 vs 26.64 | Helped |
| Use res-clique blocks instead of residual blocks in FEN (ablation) | SRCliqueNet · Set5 2× | PSNR/SSIM | Helped |
| Use res-clique blocks instead of dense blocks in FEN (ablation) | SRCliqueNet · Set5 2× | PSNR/SSIM | Helped |
| Use clique up-sampling instead of deconvolution (ablation) | SRCliqueNet · Set5 2× | PSNR/SSIM | Helped |
| Use clique up-sampling instead of sub-pixel convolution (ablation) | SRCliqueNet · Set5 2× | PSNR/SSIM | Helped |
Closest papers by meaning
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017 · similarity 0.88)
- ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic (CVPR 2021 · similarity 0.87)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.86)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.86)
- Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution (CVPR 2024 · similarity 0.85)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.85)
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.