Research map / Image generation / Image restoration
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring
Jiangxin Dong, Stefan Roth, Bernt Schiele
Check 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 |
|---|---|---|---|
| jointly learn image-adaptive data and regularization terms (ablation) | SVMAP · Martin et al. [24], 1% Gaussian noise | PSNR (dB): 29.88 -> 31.89; 31.59 -> 31.89 | Improved |
| jointly learn image-adaptive data and regularization terms (ablation) | SVMAP · Saturated-pixel dataset | PSNR (dB): 30.58 -> 33.91; 29.47 -> 33.91 | Improved |
| add spatially-variant filters instead of spatially-invariant filters (ablation) | SVMAP · Martin et al. [24], 1% Gaussian noise | PSNR (dB)/SSIM: 31.25/0.8861 -> 31.89/0.8973 | Improved |
| add spatially-variant filters instead of spatially-invariant filters (ablation) | SVMAP · Martin et al. [24], 5% Gaussian noise | PSNR (dB)/SSIM: 26.72/0.7302 -> 27.25/0.7550 | Improved |
| jointly learn data and regularization terms with spatially-variant features | SVMAP · Martin et al. [24], 1% noise | PSNR (dB): 30.92 -> 31.89 | Improved |
| jointly learn data and regularization terms with spatially-variant features | SVMAP · Martin et al. [24], 5% noise | PSNR (dB): 25.93 -> 27.25 | Improved |
| jointly learn data and regularization terms with spatially-variant features | SVMAP · Sun et al. [41], 1% noise | PSNR (dB): 33.57 -> 34.51 | Improved |
| jointly learn data and regularization terms with spatially-variant features | SVMAP · Sun et al. [41], 5% noise | PSNR (dB): 27.75 -> 29.20 | Improved |
| jointly learn data and regularization terms with spatially-variant features | SVMAP · Saturated-pixel dataset | PSNR (dB): 33.02 -> 33.91 | Improved |
Closest papers by meaning
- Deep Richardson–Lucy Deconvolution for Low-Light Image Deblurring (IJCV 2023 · similarity 0.89)
- Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks (CVPR 2018 · similarity 0.89)
- End-to-end Interpretable Learning of Non-blind Image Deblurring (ECCV 2020 · similarity 0.89)
- Noise-Blind Image Deblurring (CVPR 2017 · similarity 0.89)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 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.
