Research map / Learning theory and algorithms / Kernels and regression theory
Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution
Check 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 proposed method instead of Vasu et al. [43] | Non-blind deconvolution on Levin et al.'s dataset with kernel [7] · Levin et al.'s dataset, kernel [7] | PSNR (dB): 30.62 -> 30.92 | Helped |
| Use the proposed method instead of Vasu et al. [43] | Non-blind deconvolution on Sun et al.'s dataset with kernel [45] · Sun et al.'s dataset, kernel [45] | PSNR (dB): 32.60 -> 32.76 | Helped |
| Use the proposed method instead of Vasu et al. [43] | Non-blind deconvolution on Lai et al.'s dataset with kernel [45] · Lai et al.'s dataset, kernel [45] | PSNR (dB): 22.90 -> 24.83 | Helped |
| Add the DP-Unet correction module (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [7] · Levin et al.'s dataset, kernel [7] | PSNR (dB): 30.61 -> 30.92 | Helped |
| Add the DP-Unet correction module (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [25] · Levin et al.'s dataset, kernel [25] | PSNR (dB): 30.85 -> 31.14 | Helped |
| Add the DP-Unet correction module (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [30] · Levin et al.'s dataset, kernel [30] | PSNR (dB): 34.30 -> 34.66 | Helped |
| Add the DP-Unet correction module (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [41] · Levin et al.'s dataset, kernel [41] | PSNR (dB): 32.90 -> 33.36 | Helped |
| Train with kernels generated by the proposed synthesis procedure (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [7] · Levin et al.'s dataset, kernel [7] | PSNR (dB): 30.06 -> 30.92 | Helped |
| Train with kernels generated by the proposed synthesis procedure (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [25] · Levin et al.'s dataset, kernel [25] | PSNR (dB): 30.35 -> 31.14 | Helped |
| Train with kernels generated by the proposed synthesis procedure (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [30] · Levin et al.'s dataset, kernel [30] | PSNR (dB): 33.86 -> 34.66 | Helped |
| Train with kernels generated by the proposed synthesis procedure (ablation) | Proposed deconvolution network on Levin et al.'s dataset, kernel [41] · Levin et al.'s dataset, kernel [41] | PSNR (dB): 32.39 -> 33.36 | Helped |
Closest papers by meaning
- Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs (CVPR 2018 · similarity 0.93)
- Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior (CVPR 2023 · similarity 0.90)
- Neural Blind Deconvolution Using Deep Priors (CVPR 2020 · similarity 0.90)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.86)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.86)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · similarity 0.85)
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.