Research map / Video / Video segmentation and tracking
Efficient Video Deblurring Guided by Motion Magnitude
Yusheng Wang, Yunfan Lu, Ye Gao, Lin Wang, Zhihang Zhong, Yinqiang Zheng, Atsushi Yamashita
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 MMAM with MMP (ablation) | MMP-RNN · GOPRO | PSNR: 32.33 -> 32.64 | Improved |
| add motion magnitude loss (ablation) | MMP-RNN · GOPRO | PSNR: 32.25 -> 32.33 | Improved |
| add transmission of non-deblurred features (ablation) | MMP-RNN · GOPRO | PSNR: 32.06 -> 32.25 | Improved |
| add MMAM with MMP (ablation) | MMP-RNN · BSD | PSNR: 32.16 -> 32.79 | Improved |
| add motion magnitude loss (ablation) | MMP-RNN · BSD | PSNR: 32.07 -> 32.16 | Improved |
| add transmission of non-deblurred features (ablation) | MMP-RNN · BSD | PSNR: 32.03 -> 32.07 | Improved |
| add estimated MMP prior (ablation) | MMP-RNN small · GOPRO | PSNR: 30.17 -> 30.48 | Improved |
| use ground-truth MMP instead of estimated MMP (ablation) | MMP-RNN small · GOPRO | PSNR: 30.48 -> 30.54 | Improved |
| use center-frame flow magnitude as prior instead of none (ablation) | MMP-RNN small · GOPRO | PSNR: 30.17 -> 30.47 | Improved |
| replace MMP and MMAM with spatial self-attention (ablation) | MMP-RNN small · GOPRO | PSNR: 30.48 -> 30.37 | Hurt |
| normalize each ground-truth MMP map to 0-1 (ablation) | MMP-RNN small · GOPRO | PSNR: 30.54 -> 30.41 | Hurt |
Closest papers by meaning
- Deep Video Deblurring for Hand-Held Cameras (CVPR 2017 · similarity 0.91)
- Dynamic Video Deblurring Using a Locally Adaptive Blur Model (TPAMI 2017 · similarity 0.91)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-Local Spatial-Temporal Similarity (TPAMI 2023 · similarity 0.90)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.89)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.89)
- 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.
