Research map / Video / Video segmentation and tracking
Dynamic Video Deblurring Using a Locally Adaptive Blur Model
Tae Hyun Kim, Seungjun Nah, Kyoung Mu Lee
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 defocus blur map estimation to the deblurring model (ablation) | Ours · Motion+Gaussian blur dataset, avg | PSNR: 28.11 -> 28.73 | Improved |
| add defocus blur map estimation (ablation) | Ours · Motion+Gaussian blur dataset, avg | SSIM: 0.8363 -> 0.9367 | Improved |
| apply deblurring to motion-blurred videos | Ours (w/o defocus) · Motion blur only dataset, avg | PSNR: 28.42 -> 30.52 | Improved |
| apply deblurring to motion-blurred videos | Ours (w/o defocus) · Motion blur only dataset, avg | SSIM: 0.8521 -> 0.9037 | Improved |
| apply full deblurring to motion+Gaussian blurred videos | Ours (full) · Motion+Gaussian blur dataset, avg | PSNR: 26.76 -> 28.73 | Improved |
| add defocus modeling on sequence #9 (ablation) | Ours · Motion+Gaussian blur, seq #9 | PSNR: 29.05 -> 27.74 | Hurt |
| add defocus modeling on sequence #4 (ablation) | Ours · Motion+Gaussian blur, seq #4 | PSNR: 36.50 -> 36.36 | No clear effect |
| add temporal coherence term (ablation) | Ours · real blurry videos | qualitative | Improved |
Closest papers by meaning
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.91)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.90)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.90)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.90)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.89)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · similarity 0.89)
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.
