Research map / Image generation / Image restoration
Enhanced Sparse Model for Blind Deblurring
Liang Chen, Faming Fang, Shen Lei, Fang Li, Guixu Zhang
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 l_e instead of l0 to regularize the latent image gradient (ablation) | l_e deblurring model · Levin et al. dataset | success percent vs error ratio | Improved |
| add l_e on gradient domain (l2 + grad l_e) in noise fitting (ablation) | l_e deblurring model · Levin et al. dataset | success percent vs error ratio | Improved |
| add a sparse term to the l2-only noise model (ablation) | noise fitting term · Levin et al. dataset | success percent vs error ratio | Improved |
| use l_e on gradient domain instead of intensity domain for noise term (ablation) | noise fitting term · Levin et al. dataset | success percent vs error ratio | Improved |
| increase sparsity of the sparse component from l1 to l_e (ablation) | noise fitting term · Levin et al. dataset | success percent vs error ratio | Improved |
| vary beta weight of the sparse noise term (ablation) | l_e deblurring model · Levin et al. dataset | average PSNR: 0.001 to 0.005 | Mixed |
| vary gamma kernel smoothness weight (ablation) | l_e deblurring model · Levin et al. dataset | average PSNR | No clear effect |
| vary theta image gradient weight (ablation) | l_e deblurring model · Levin et al. dataset | average PSNR: 0.002 to 0.008 | Mixed |
Closest papers by meaning
- Deblurring Natural Image Using Super-Gaussian Fields (ECCV 2018 · similarity 0.90)
- Blind Deblurring for Saturated Images (CVPR 2021 · similarity 0.89)
- Blind Image Deblurring With Local Maximum Gradient Prior (CVPR 2019 · similarity 0.89)
- Noise-Blind Image Deblurring (CVPR 2017 · similarity 0.89)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 2024 · similarity 0.87)
- Robust Blind Text Image Deblurring via Maximum Consensus Framework (AAAI 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.
