Research map / Image generation / Super-resolution
Blind Image Super-Resolution With Elaborate Degradation Modeling on Noise and Kernel
Zongsheng Yue, Qian Zhao, Jianwen Xie, Lei Zhang, Deyu Meng, Kwan-Yee K. Wong
Check 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 BSRDM rather than DIPFKP | Blind SISR · Set14, Case 2 camera sensor noise, ×2 | PSNR: 26.95 -> 28.01 | Improved |
| Use BSRDM rather than ZSSR-NB | Blind SISR · Set14, Case 1 Gaussian noise, ×2 | PSNR: 30.27 -> 29.56 | Hurt |
| Use BSRDM rather than DIPFKP | Blind SISR · Set14, Case 1 Gaussian noise, ×3 | PSNR: 26.59 -> 28.19 | Improved |
| Replace i.i.d. noise with patch-based non-i.i.d. noise (ablation) | BSRDM with EKP · Set14, camera sensor noise, ×2, six kernels | PSNR: 27.76 -> 28.01 | Improved |
| Replace FKP with EKP (ablation) | BSRDM with patch-based non-i.i.d. noise · Set14, camera sensor noise, ×2, six kernels | PSNR: 27.52 -> 28.01 | Improved |
| Set hyper-Laplacian weight ρ to 0 rather than 0.20 (ablation) | BSRDM · Set14, camera sensor noise, ×2, six kernels | PSNR: 28.01 -> 27.20 | Hurt |
| Set hyper-Laplacian weight ρ to 0.40 rather than 0.20 (ablation) | BSRDM · Set14, camera sensor noise, ×2, six kernels | PSNR: 28.01 -> 28.09 | No clear effect |
| Set hyper-Laplacian weight ρ to 1.00 rather than 0.20 (ablation) | BSRDM · Set14, camera sensor noise, ×2, six kernels | PSNR: 28.01 -> 27.56 | Hurt |
| Set gradient-prior exponent γ to 1.00 rather than 0.67 (ablation) | BSRDM · Set14, camera sensor noise, ×2, six kernels | PSNR: 28.01 -> 27.83 | Hurt |
| Set gradient-prior exponent γ to 2.00 rather than 0.67 (ablation) | BSRDM · Set14, camera sensor noise, ×2, six kernels | PSNR: 28.01 -> 27.27 | Hurt |
Closest papers by meaning
- Blind Super-Resolution via Meta-Learning and Markov Chain Monte Carlo Simulation (TPAMI 2024 · similarity 0.92)
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV 2021 · similarity 0.92)
- Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · similarity 0.91)
- Spatially-Variant Degradation Model for Dataset-free Super-resolution (ECCV 2024 · similarity 0.90)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · similarity 0.89)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.88)
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.
