Research map / Learning theory and algorithms / Matrix and tensor methods
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
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 |
|---|---|---|---|
| GLRA separable-filter initialization instead of random initialization (ablation) | deconvolution CNN · Figure 7 feature maps | visual quality / feature sharpness | Helped |
| vary inverse-kernel size d (120 to 170) and M size m (35 to 60) (ablation) | GLRA network · testing set | PSNR/SSIM | No clear effect |
| use GLRA network instead of VEM on Gaussian blur | VEM · Gaussian blur with saturated pixels | PSNR: 24.0954 -> 25.6931 | Helped |
| use GLRA network instead of VEM on Gaussian blur | VEM · Gaussian blur with saturated pixels | SSIM: 0.8822 -> 0.8768 | Hurt |
| use GLRA network instead of IRCNN on BSD100 Gaussian blur | IRCNN · BSD100 Gaussian blur | PSNR: 22.3735 -> 23.2141 | Helped |
| use GLRA network instead of IRCNN on BSD100 Gaussian blur | IRCNN · BSD100 Gaussian blur | SSIM: 0.8012 -> 0.7730 | Hurt |
| use GLRA network on motion blur kernels instead of MLP | MLP · motion blur example | PSNR/SSIM | Hurt |
Closest papers by meaning
- Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution (CVPR 2017 · similarity 0.90)
- Neural Blind Deconvolution Using Deep Priors (CVPR 2020 · similarity 0.90)
- Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs (CVPR 2018 · similarity 0.89)
- Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring (NeurIPS 2020 · similarity 0.89)
- Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution (CVPR 2020 · similarity 0.88)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 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.