Research map / Image generation / Image restoration
Multi-Level Blur-Aware Stable Diffusion for Region-Adaptive Defocus Deblurring
Xiaopan Li, Yi Jiang, Shiqian Wu, Shoulie Xie, Sos Agaian
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 |
|---|---|---|---|
| add PBA blur-level labels as expert weights in BAEM over BRDM baseline (ablation) | MBSD · DPDD | PSNR: 25.12 -> 25.49 | Improved |
| add MSBE soft blur probabilities instead of discrete PBA labels (ablation) | MBSD · DPDD | PSNR: 25.49 -> 25.97 | Improved |
| add MSBE soft blur probabilities instead of discrete PBA labels (ablation) | MBSD · DPDD | LPIPS: 0.123 -> 0.109 | Improved |
| add fidelity restoration loss (ablation) | MBSD · DPDD | PSNR: 25.97 -> 26.55 | Improved |
| add fidelity restoration loss (ablation) | MBSD · DPDD | SSIM: 0.789 -> 0.800 | Improved |
| add fidelity restoration loss (ablation) | MBSD · DPDD | LPIPS: 0.109 -> 0.106 | Improved |
| MBSD versus best baseline on SSIM | MBSD · DPDD | SSIM: 0.814 -> 0.800 | Hurt |
| MBSD versus best baseline on SSIM | MBSD · RealDOF (trained on DPDD) | SSIM: 0.787 -> 0.769 | Hurt |
| use re-blur Blur Score instead of NIQE for blur level (ablation) | PBA · Gaussian-blurred DPDD images | monotonicity with blur strength | 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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 3 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
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.91)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.90)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring (AAAI 2024 · similarity 0.88)
- Visual-Instructed Degradation Diffusion for All-in-One Image Restoration (CVPR 2025 · similarity 0.88)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 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.
