Research map / Image generation / Super-resolution
A New Dataset and Framework for Real-World Blurred Images Super-Resolution
Rui Qin, Ming Sun, Chao Zhou, Bin Wang
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 |
|---|---|---|---|
| train unified on mixed blur and general data instead of separate data types (ablation) | FeMaSR · ReBlurSR-Test and general data | LPIPS | Hurt |
| average two CDM branches after training without CFM (ablation) | CDM_FeMaSR · ReBlurSR-Test (blur data) | LPIPS: 0.3714 -> 0.3711 | No clear effect |
| add cross fusion module (CFM) during CDM training (ablation) | PBaSR · general and blur data | LPIPS: 0.01-0.015 LPIPS | Improved |
| condition discriminator on blur map in blur branch (ablation) | FeMaSR blur branch · ReBlurSR-Test HR | LPIPS on blur samples: 0.022 LPIPS improvement | Improved |
| add synthetic blur images to ReBlurSR training data (ablation) | FeMaSR · ReBlurSR-Test (blur data) | LPIPS: about 0.013 LPIPS | Improved |
| CFM interpolation communication every iteration (k=1) or every 100 (k=100) instead of k=20 (ablation) | PBaSR_FeMaSR · ReBlurSR-Test (Defocus) | LPIPS: 0.005-0.01 LPIPS | Hurt |
| use lambda0 between 0.9 and 0.99 instead of 0 or 1 (ablation) | PBaSR_FeMaSR · ReBlurSR-Test (Defocus) | LPIPS | Improved |
| use CFM weight interpolation instead of cross feature distillation or dual teacher-student (ablation) | PBaSR · blur and general data | LPIPS: 0.006 to 0.008 LPIPS | Improved |
| apply PBaSR to FeMaSR vs best prior on blur data (HAT) | PBaSR_FeMaSR · ReBlurSR-Test | LPIPS: 0.3924 -> 0.3564 | Improved |
| apply PBaSR to Real-ESRGAN vs gan artifact correction methods LDL and DeSRA | Real-ESRGAN · ReBlurSR-Test and general | LPIPS: 0.007-0.02 LPIPS on blur data | Improved |
| add defocus blur training data progressively (ablation) | PBaSR · ReBlurSR-Test (defocus) | LPIPS: 0.04 LPIPS | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SRFormer — SRFormer: Permuted Self-Attention for Single Image Super-Resolution (ICCV 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Blind Image Super-Resolution: A Survey and Beyond (TPAMI 2022 · similarity 0.90)
- End-to-End Alternating Optimization for Real-World Blind Super Resolution (IJCV 2023 · similarity 0.89)
- Learning the Non-Differentiable Optimization for Blind Super-Resolution (CVPR 2021 · similarity 0.88)
- Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution (CVPR 2024 · similarity 0.88)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.87)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · 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.
