Research map / Image generation / Super-resolution
Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution
Liangbin Xie, Xintao Wang, Chao Dong, Zhongang Qi, Ying Shan
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 |
|---|---|---|---|
| Replace the two-branch architecture with a one-branch SRResNet | DAN and DASR blind SR · Blur and blur+noise | PSNR (dB): DAN blur: 26.168±0.009 -> 26.182±0.011; DAN blur+noise: 27.341±0.072 -> 27.288±0.027; DASR blur: 27.518±0.034 -> 27.573± | No clear effect |
| Use FAIG rather than IG to select the filters to mask (ablation) | SRResNet blind SR · Set14 blurry and noisy images | Image-gradient MSE performance drop (10^-3): Blurry, 1%: 4.31±1.54 -> 6.68±0.63; noisy, 1%: 4.22±0.44 -> 6.62±0.54; blurry, 5%: 6.41±0.88 -> 7.53±0.24; noisy, 5%: 8. | Improved |
| Use FAIG rather than absolute filter changes to select the filters to mask (ablation) | SRResNet blind SR · Set14 blurry and noisy images | Image-gradient MSE performance drop (10^-3): Blurry, 1%: 0.18±0.13 -> 6.68±0.63; noisy, 1%: 0.49±0.10 -> 6.62±0.54; blurry, 5%: 2.16±0.61 -> 7.53±0.24; noisy, 5%: 3. | Improved |
| Use FAIG rather than random selection to choose filters to mask (ablation) | SRResNet blind SR · Set14 blurry and noisy images | Image-gradient MSE performance drop (10^-3): Blurry, 1%: 0.07±0.01 -> 6.68±0.63; noisy, 1%: 0.04±0.01 -> 6.62±0.54; blurry, 5%: 0.55±0.32 -> 7.53±0.24; noisy, 5%: 0. | Improved |
| Retrain only FAIG-selected filters at their selected locations rather than randomly selected filters (ablation) | Baseline SRResNet · Set14 blurry images, train for deblurring | PSNR (dB): 27.028 -> 28.047 | Improved |
| Retrain only FAIG-selected filters at their selected locations rather than randomly selected filters (ablation) | Baseline SRResNet · Set14 noisy images, train for denoising | PSNR (dB): 25.526 -> 25.793 | Improved |
| Apply deblurring-selected filters to denoising rather than retraining denoising-selected filters (ablation) | Baseline SRResNet · Set14 blurry images, train for deblurring | PSNR (dB): 27.463 -> 28.047 | Hurt |
| Apply denoising-selected filters to deblurring rather than retraining deblurring-selected filters (ablation) | Baseline SRResNet · Set14 noisy images, train for denoising | PSNR (dB): 25.590 -> 25.793 | Hurt |
| Remove gradient elimination for other degradations when selecting deblurring filters (ablation) | FAIG filter selection · Noisy inputs with 1% deblurring filters masked | Denoising function retained | Hurt |
| Use overlap of discovered filter sets to predict degradation without supervised degradation labels | FAIG degradation prediction · DIV2K | Prediction accuracy: 98% noise; 96% blur | Improved |
Closest papers by meaning
- Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution (ICCV 2023 · similarity 0.91)
- Unsupervised Degradation Representation Learning for Blind Super-Resolution (CVPR 2021 · similarity 0.91)
- Knowledge Distillation based Degradation Estimation for Blind Super-Resolution (ICLR 2023 · similarity 0.91)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.89)
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · similarity 0.89)
- Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution (CVPR 2024 · similarity 0.87)
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.
