Research map / Video / Video segmentation and tracking
Bringing Alive Blurred Moments
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 proposed deblurring network instead of the strongest competing method | Single-image deblurring · GoPro test | PSNR: 30.10 -> 30.58 | Helped |
| Use the proposed deblurring network instead of the strongest competing method | Single-image deblurring · GoPro test | SSIM: 0.933 -> 0.941 | Helped |
| Use the proposed deblurring network instead of the strongest competing method | Single-image deblurring · GoPro test | inference time: 0.4 -> 0.02 | Helped |
| Use the proposed deblurring network instead of the strongest competing method | Single-image deblurring · GoPro test | model size: 27.5 -> 17.9 | Helped |
| Use the proposed video extraction method instead of the competing method | Video extraction · 7-frame blur | ambiguity-invariant error: 49.06 -> 44.12 | Helped |
| Generate video from a 9-frame blur rather than a 7-frame blur | Ours · Video extraction | ambiguity-invariant error: 44.12 -> 48.24 | Mixed |
| Estimate optical flow rather than directly estimate frame intensities (ablation) | Video autoencoder · Video reconstruction | video generation quality | Helped |
| Use a recurrent decoder to generate the sequence (ablation) | Video extraction · Video generation | temporal consistency | Helped |
| Train BIE with a pretrained RVD in the two-stage strategy rather than train BIE and RVD directly from scratch (ablation) | BIE-RVD · Video extraction | video generation quality | Helped |
| Provide the central sharp frame as an additional BIE input (ablation) | BIE · Video extraction | video generation quality | Helped |
Closest papers by meaning
- Learning to Extract a Video Sequence From a Single Motion-Blurred Image (CVPR 2018 · similarity 0.92)
- Learning to Synthesize Motion Blur (CVPR 2019 · similarity 0.90)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.87)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.87)
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 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.