Research map / Video / Video segmentation and tracking
Exposure Trajectory Recovery From Motion Blur
Youjian Zhang, Chaoyue Wang, Stephen J. Maybank, Dacheng Tao
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 |
|---|---|---|---|
| replace linear with quadratic trajectory constraint (ablation) | motion offset estimation · Synthetic reblurring | PSNR: 37.34 -> 38.9 | Improved |
| use bi-directional linear instead of linear constraint (ablation) | motion offset estimation · Synthetic reblurring | PSNR: 37.34 -> 38.64 | Improved |
| add quadratic constraint instead of zero constraint (ablation) | motion offset estimation · GoPro reblurring | PSNR: 35.82 -> 34.68 | Hurt |
| add quadratic trajectory constraint instead of zero constraint for deblurring guidance (ablation) | DMPHN with MA Conv · GoPro deblurring | PSNR: 30.79 -> 31.05 | Improved |
| add motion-aware convolution to DMPHN (ablation) | DMPHN · GoPro deblurring | PSNR: 30.21 -> 31.05 | Improved |
| add motion-aware convolution to DMPHN (ablation) | DMPHN · GoPro deblurring | SSIM: 0.9345 -> 0.9485 | Improved |
| increase offsets from 5 to 15 (ablation) | motion offset estimation · GoPro reblurring | PSNR: 34.09 -> 34.68 | Improved |
| increase offsets from 9 to 15 (ablation) | motion offset estimation · GoPro reblurring | PSNR: 34.52 -> 34.68 | Improved |
| add SSIM loss (ablation) | motion offset estimation · GoPro reblurring | PSNR: 34.16 -> 34.68 | Improved |
| add total variation loss (ablation) | motion offset estimation · GoPro reblurring | PSNR: 33.96 -> 34.68 | Improved |
| add offset regularization loss (ablation) | motion offset estimation · GoPro reblurring | PSNR: 34.56 -> 34.68 | No clear effect |
| add our motion offsets to Jin et al. frames for warping | Jin et al. · GoPro video extraction | EPE: 9.32 -> 6.07 | Improved |
Closest papers by meaning
- Event-Guided Deblurring of Unknown Exposure Time Videos (ECCV 2022 · similarity 0.90)
- Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time (CVPR 2023 · similarity 0.89)
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (CVPR 2017 · similarity 0.89)
- Motion Blur Decomposition with Cross-shutter Guidance (CVPR 2024 · similarity 0.88)
- ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation (CVPR 2024 · similarity 0.87)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.87)
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.
