Research map / Image generation / Image restoration
A Neural Approach to Blind Motion Deblurring
Ayan Chakrabarti
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 global kernel estimation and EPLL non-blind deconvolution on top of the neural average (ablation) | Proposed · Sun et al. benchmark (640 images) | success rate (r<=5): 61% -> 92% | Improved |
| add global kernel estimation and EPLL non-blind deconvolution on top of the neural average (ablation) | Proposed · Sun et al. benchmark (640 images) | mean error ratio: 4.92 -> 3.01 | Improved |
| add global kernel estimation and EPLL non-blind deconvolution on top of the neural average (ablation) | Proposed · Sun et al. benchmark (640 images) | max error ratio: 19.11 -> 11.04 | Improved |
| use the neural network approach instead of iterative methods (Sun et al.) for kernel estimation | Proposed · Sun et al. benchmark (640 images) | kernel estimation time: 38min (CPU) -> 65s (GPU) | Improved |
| use the neural method instead of Michaeli & Irani | Proposed · Sun et al. benchmark (640 images) | mean error ratio: 2.57 -> 3.01 | Hurt |
| use the neural method instead of Schuler et al. neural architecture | Proposed · Sun et al. benchmark (640 images) | success rate (r<=5): 67% -> 92% | Improved |
Closest papers by meaning
- Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs (CVPR 2018 · similarity 0.93)
- Blur-Invariant Deep Learning for Blind-Deblurring (ICCV 2017 · similarity 0.92)
- Neural Blind Deconvolution Using Deep Priors (CVPR 2020 · similarity 0.91)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.91)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · similarity 0.90)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · 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.
