Research map / Image generation / Image restoration
Scale-Wise Convolution for Image Restoration
Yuchen Fan, Jiahui Yu, Ding Liu, Thomas S. Huang
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 |
|---|---|---|---|
| Use scale-wise convolution rather than U-Net-style multi-scale fusion (ablation) | SCN · Super-resolution ×2 | PSNR: 34.56 -> 34.67 | Improved |
| Use scale-wise convolution rather than PSPNet-style multi-scale fusion (ablation) | SCN · Super-resolution ×2 | PSNR: 34.58 -> 34.67 | Improved |
| Share weights across scales instead of using un-shared weights at 1.2M parameters (ablation) | multi-scale model · Super-resolution ×2 | PSNR: 34.68 -> 34.77 | Improved |
| Use a larger un-shared model instead of the 1.2M shared model (ablation) | multi-scale model · Super-resolution ×2 | PSNR: 34.77 -> 34.77 | No clear effect |
| Use bilinear resampling rather than convolution/deconvolution (ablation) | SCN · Super-resolution ×2 | PSNR: 34.77 -> 34.80 | Improved |
| Use bilinear resampling rather than average/nearest resampling (ablation) | SCN · Super-resolution ×2 | PSNR: 34.78 -> 34.80 | Improved |
| Use multi-scale modeling rather than single-scale modeling (ablation) | SCN · Super-resolution ×2 | PSNR: 34.74 -> 34.67 | Improved |
| Increase the number of scales beyond the best setting (ablation) | SCN · Image restoration | PSNR | Hurt |
| Train with limited scales, then evaluate with a mismatched number of scales (ablation) | SCN · Image restoration | PSNR | Hurt |
| Train with enough scales and evaluate with additional scales (ablation) | SCN · Image restoration | PSNR | Improved |
| Mismatch scale ratios between training and evaluation (ablation) | SCN · Image restoration | PSNR | Hurt |
Closest papers by meaning
- Learning Enriched Features for Real Image Restoration and Enhancement (ECCV 2020 · similarity 0.89)
- Learning Enriched Features for Fast Image Restoration and Enhancement (TPAMI 2022 · similarity 0.89)
- Revitalizing Convolutional Network for Image Restoration (TPAMI 2024 · similarity 0.88)
- CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (NeurIPS 2020 · similarity 0.88)
- Omni-Kernel Network for Image Restoration (AAAI 2024 · similarity 0.87)
- Efficient Visual State Space Model for Image Deblurring (CVPR 2025 · 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.
