Research map / Image generation / Image restoration
Learning a Discriminative Prior for Blind Image Deblurring
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the learned discriminative CNN prior with the L0 gradient prior for blind deblurring | Proposed blind deblurring method · Text image dataset | Average PSNR: 27.94 -> 28.10 | Helped |
| Use the learned CNN prior with the L0 gradient prior rather than the L0 gradient prior alone (ablation) | Proposed blind deblurring method · Levin et al. dataset | deblurring performance | Helped |
| Remove the learned discriminative image prior (ablation) | Proposed blind deblurring method · Levin et al. dataset | strong-edge reconstruction for blur-kernel estimation | Hurt |
| Add the L0 gradient prior (ablation) | Proposed blind deblurring method · Levin et al. dataset | preservation of image structures | Helped |
| Train the classifier at multiple scales instead of only at 200 × 200 (ablation) | Binary classification network · Köhler et al. dataset at varying test image sizes | classification robustness to image size | Helped |
| Use the intensity-trained classifier on images with salt-and-pepper noise | Proposed blind deblurring method · Blurred image with salt-and-pepper noise | deblurring quality | Hurt |
Closest papers by meaning
- Blind Image Deblurring Using Dark Channel Prior (CVPR 2016 · similarity 0.90)
- Neural Blind Deconvolution Using Deep Priors (CVPR 2020 · similarity 0.90)
- Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior (CVPR 2023 · similarity 0.89)
- Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation (NeurIPS 2024 · similarity 0.88)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 2024 · similarity 0.88)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (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.