Research map / Image generation / Image restoration
Blind Noisy Image Deblurring Using Residual Guidance Strategy
Heyan Liu, Jianing Sun, Jun Liu, Xi-Le Zhao, Tingting Wu, Tieyong Zeng
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 residual guidance strategy (RGS) | Dong et al. kernel estimation · Lai et al. (sigma=0.1) | PSNR: 17.88 -> 19.45 | Improved |
| add residual guidance strategy (RGS) | Dong et al. kernel estimation · Levin et al. (sigma=0.1) | PSNR: 21.75 -> 23.37 | Improved |
| add residual guidance strategy (RGS) | Dong et al. kernel estimation · Zhang et al. faces (sigma=0.1) | PSNR: 22.89 -> 24.60 | Improved |
| add residual guidance strategy (RGS) | Dong et al. kernel estimation · RealBlur (sigma=0.1) | PSNR: 23.94 -> 24.50 | Improved |
| add RGS to Dong et al. | Dong et al. · Lai et al. (sigma=0.1) | MNC: 0.31 -> 0.66 | Improved |
| add RGS to Dong et al. | Dong et al. · Zhang et al. faces (sigma=0.1) | MNC: 0.32 -> 0.68 | Improved |
| filter the residual (RGS) instead of the blurred image via naive guidance (NGS) (ablation) | Dong et al. + guidance · Lai et al. (sigma=0.1) | PSNR: 18.96 -> 19.45 | Improved |
| filter the residual (RGS) instead of naive guidance (NGS) (ablation) | Dong et al. + guidance · Zhang et al. faces (sigma=0.1) | PSNR: 24.31 -> 24.6 | Improved |
| filter the residual (RGS) instead of naive guidance (NGS) (ablation) | Dong et al. + guidance · Lai et al. (sigma=0.1) | MNC: 0.60 -> 0.66 | Improved |
| filter the residual (RGS) instead of naive guidance (NGS) (ablation) | Dong et al. + guidance · Zhang et al. faces (sigma=0.1) | MNC: 0.67 -> 0.68 | Improved |
| NGS guidance versus no guidance on baseline (ablation) | Dong et al. · Lai et al. (sigma=0.1) | PSNR: 17.88 -> 18.96 | Improved |
Closest papers by meaning
- Blind image deblurring with noise-robust kernel estimation (ECCV 2024 · similarity 0.92)
- Blind Deblurring for Saturated Images (CVPR 2021 · similarity 0.91)
- Noise-Blind Image Deblurring (CVPR 2017 · similarity 0.89)
- Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior (CVPR 2023 · similarity 0.89)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.88)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · 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.
