Research map / 3D vision / Depth and stereo
Deep Multi-Scale Convolutional Neural Network for Dynamic Scene Deblurring
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 |
|---|---|---|---|
| Add adversarial loss to the multi-scale content loss (ablation) | Ours (K=3) · GoPro test dataset (linear CRF) | PSNR: 28.62 -> 28.45 | Hurt |
| Add adversarial loss to the multi-scale content loss (ablation) | Ours (K=3) · GoPro test dataset (linear CRF) | SSIM: 0.9094 -> 0.9170 | Helped |
| Increase the number of scales from K=1 to K=2 (ablation) | Multi-scale deblurring network · GoPro test dataset | PSNR: 28.93 -> 29.23 | Helped |
| Increase the number of scales from K=2 to K=3 (ablation) | Multi-scale deblurring network · GoPro test dataset | PSNR: 29.23 -> 29.08 | Hurt |
| Increase the number of scales from K=2 to K=3 (ablation) | Multi-scale deblurring network · GoPro test dataset | Runtime: 4.33 s -> 3.09 s | Helped |
| Increase the number of scales from K=1 to K=3 (ablation) | Multi-scale deblurring network · Köhler dataset | PSNR: 25.74 -> 26.48 | Helped |
| Increase the number of scales from K=2 to K=3 (ablation) | Multi-scale deblurring network · Köhler dataset | MSSIM: 0.8116 -> 0.8079 | Hurt |
Closest papers by meaning
- Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training (CVPR 2020 · similarity 0.93)
- Region-Adaptive Dense Network for Efficient Motion Deblurring (AAAI 2020 · similarity 0.92)
- Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks (CVPR 2018 · similarity 0.91)
- Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring (CVPR 2024 · similarity 0.91)
- Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs (CVPR 2018 · similarity 0.91)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.90)
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.