Research map / Video / Video segmentation and tracking
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
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 |
|---|---|---|---|
| Use the cascaded method rather than estimating flow from blurred inputs without cascaded training (ablation) | CDVD-TSP · Su et al. video deblurring test set | PSNR: 31.33 -> 32.13 | Helped |
| Use the cascaded method rather than estimating flow from blurred inputs without cascaded training (ablation) | CDVD-TSP · Su et al. video deblurring test set | SSIM: 0.9125 -> 0.9268 | Helped |
| Increase the cascade from two stages to three (ablation) | CDVD-TSP · Su et al. video deblurring test set | PSNR: 32.13 -> 32.20 | Helped |
| Increase the cascade from two stages to three (ablation) | CDVD-TSP · Su et al. video deblurring test set | SSIM: 0.9268 -> 0.9272 | Helped |
| Add the temporal sharpness prior (ablation) | CDVD-TSP · Four high-blur test videos | PSNR: 34.48 -> 34.63 | Helped |
| Add the temporal sharpness prior (ablation) | CDVD-TSP · Four high-blur test videos | SSIM: 0.9126 -> 0.9268 | Helped |
| Add the temporal sharpness prior (ablation) | CDVD-TSP · Three videos with blur at every position | PSNR: 31.31 -> 31.33 | No clear effect |
| Add the temporal sharpness prior (ablation) | CDVD-TSP · Three videos with blur at every position | SSIM: 0.9238 -> 0.9239 | No clear effect |
| Add optical flow estimation (ablation) | CDVD-TSP · Su et al. video deblurring test set | PSNR: 31.19 -> 32.13 | Helped |
| Add optical flow estimation (ablation) | CDVD-TSP · Su et al. video deblurring test set | SSIM: 0.9055 -> 0.9268 | Helped |
| Replace PWC-Net with FlowNet 2.0 (ablation) | CDVD-TSP · Su et al. video deblurring test set | PSNR: 32.13 -> 32.06 | Hurt |
| Replace PWC-Net with FlowNet 2.0 (ablation) | CDVD-TSP · Su et al. video deblurring test set | SSIM: 0.9268 -> 0.9254 | Hurt |
Closest papers by meaning
- Multi-Scale Memory-Based Video Deblurring (CVPR 2022 · similarity 0.89)
- Deep Video Deblurring for Hand-Held Cameras (CVPR 2017 · similarity 0.89)
- Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training (CVPR 2020 · similarity 0.89)
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring (AAAI 2022 · similarity 0.89)
- Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring (CVPR 2019 · similarity 0.88)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.86)
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.