Research map / Video / Video segmentation and tracking
Event-driven Motion Deblurring via Trajectory-based Kernel Reconstruction
Zhiwei Zhong, Peilin CHEN, Wei Dong, Bo Li, Anmin Liu, Shiqi Wang
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 |
|---|---|---|---|
| use event-derived spatially varying blur operator instead of a learnable standard convolution (ablation) | unrolled deblurring network · GoPro | PSNR: 36.25 -> 37.15 | Improved |
| add event consistency term to the joint objective (ablation) | unrolled deblurring network · GoPro | PSNR: 36.60 -> 37.15 | Improved |
| increase number of temporal bins M (ablation) | kernel estimation · GoPro | PSNR/SSIM | Improved |
| increase kernel size beyond 5x5 (ablation) | PSF kernels · GoPro | PSNR/SSIM | No clear effect |
| increase number of unrolled stages N (ablation) | unrolled network · GoPro | PSNR | Improved |
| event-guided physical kernel framework vs best prior event methods | proposed method · GoPro | PSNR: 36.78 -> 37.15 | Improved |
| event-guided physical kernel framework vs best prior method | proposed method · HS-ERGB | PSNR: 28.97 -> 29.43 | Improved |
| event-guided physical kernel framework vs best prior method | proposed method · REBlur | PSNR: 36.97 -> 37.24 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CMTA-7 — CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Event-based Motion Deblurring with Unpaired Data (CVPR 2026 · similarity 0.93)
- Event-Based Motion Deblurring Using Task-Oriented 3D Gaussian Event Representations (CVPR 2026 · similarity 0.93)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.91)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.89)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.89)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · 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.
