Research map / Image generation / Image restoration
Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior
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 Ours instead of Fang et al. | Semi-blind deblurring · Levin dataset (average) | PSNR: 30.27 -> 31.01 | Helped |
| Use Ours instead of Fang et al. | Semi-blind deblurring · Levin dataset (average) | SSIM: 0.87 -> 0.89 | Helped |
| Use Ours instead of Fang et al. | Semi-blind deblurring · Lai dataset (average) | PSNR: 20.31 -> 20.84 | Helped |
| Use Ours instead of Fang et al. | Semi-blind deblurring · Lai dataset (average) | SSIM: 0.66 -> 0.68 | Helped |
| add sparse prior for residual (ablation) | Ours · Ablation test images (24 images) | PSNR: 26.77 -> 28.64 | Helped |
| add sparse prior for DCT artifacts (ablation) | Ours · Ablation test images (24 images) | PSNR: 27.25 -> 28.64 | Helped |
| add total variation prior for image (ablation) | Ours · Ablation test images (24 images) | PSNR: 27.98 -> 28.64 | Helped |
| add DIP for image (ablation) | Ours · Ablation test images (24 images) | PSNR: 26.54 -> 28.64 | Helped |
| add DRP for residual (ablation) | Ours · Ablation test images (24 images) | PSNR: 25.69 -> 28.64 | Helped |
| replace sigmoid with soft-shrinkage in the residual network (ablation) | DRP · Deblurring and residual estimation (illustrative comparison) | image restoration quality | Helped |
Closest papers by meaning
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.90)
- Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring (AAAI 2024 · similarity 0.89)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.88)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 2024 · similarity 0.88)
- Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation (NeurIPS 2024 · similarity 0.87)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · similarity 0.86)
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.