Research map / Video / Video segmentation and tracking
EVDM: Event-based Real-world Video Deblurring with Mamba
Zhijing Sun, Senyan Xu, Kean Liu, Runze Tian, Xueyang Fu, Zheng-Jun Zha
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 ResBlock event branch with MCEM plus event self-reconstruction loss (ablation) | EVDM · EVRB | PSNR: 31.32 -> 31.63 | Improved |
| replace self-attention event branch with MCEM plus Lesr (ablation) | EVDM · EVRB | FLOPs: 30.88 -> 17.92 | Improved |
| add event self-reconstruction loss to MCEM (ablation) | EVDM · EVRB | PSNR: 31.48 -> 31.63 | Improved |
| add event self-reconstruction loss to MCEM (ablation) | EVDM · EVRB | SSIM: 0.902 -> 0.919 | Improved |
| add MIFM to baseline (ablation) | EVDM · EVRB | PSNR: 30.57 -> 30.90 | Improved |
| add ITPM to baseline (ablation) | EVDM · EVRB | PSNR: 30.57 -> 30.78 | Improved |
| use motion-aware state space instead of standard BiMamba in MIFM and ITPM (ablation) | EVDM · EVRB | PSNR: 30.63 -> 31.63 | Improved |
| combine MIFM and ITPM with MSS (ablation) | EVDM · EVRB | PSNR: 30.57 -> 31.63 | Improved |
| increase input frames from 3 to 15 | EVDM · EVRB | PSNR: 31.64 -> 32.05 | Improved |
| increase input frames from 3 to 15 | EVDM · T-RED | PSNR: 29.99 -> 30.19 | Improved |
| increase input frames from 3 to 15 | EVDM · EVRB | SSIM: 0.934 -> 0.938 | Improved |
| use EVDM instead of CMTA-5 | EVDM · GoPro | PSNR: 36.55 -> 36.99 | 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-5 — CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring (ECCV 2024) · better on 2 of 2 shared results
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
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.91)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.89)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.89)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.88)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.88)
- EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction (AAAI 2025 · similarity 0.88)
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.
