Research map / Image generation / Image restoration
From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur
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 |
|---|---|---|---|
| Estimate dense motion flow with a whole-image FCN instead of patch-level CNN processing | Motion blur removal · BSD-S and BSD-M | motion-flow MSE: 50.1168 -> 6.6198; 15.6389 -> 5.2051 | Helped |
| Estimate dense motion flow with a whole-image FCN instead of patch-level CNN processing | Motion blur removal · BSD-S and BSD-M | PSNR: 20.534 -> 21.947; 22.9683 -> 23.978 | Helped |
| Train on simulated BSD motion-flow data and evaluate on COCO images | Motion blur removal · MC-S and MC-M | motion-flow MSE: 52.1234 -> 7.8038; 22.4383 -> 7.3405 | Helped |
| Use the whole-image FCN motion-flow estimator instead of patchCNN | Motion blur removal · 640×480 images | time (s): 45.2 -> 8.4 | Helped |
Closest papers by meaning
- Optical Flow Estimation from a Single Motion-blurred Image (AAAI 2021 · similarity 0.92)
- Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring (CVPR 2023 · similarity 0.91)
- Learning to Synthesize Motion Blur (CVPR 2019 · similarity 0.90)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.89)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · 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.