Research map / Video / Video segmentation and tracking
Time-Specialized Event-Image Alignment for Blur-to-Video Decomposition
Zhijing Sun, Senyan Xu, Ruixuan Jiang, 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 |
|---|---|---|---|
| add Relative Time-Encoded Attention (ablation) | TSANet baseline (Case 1) · HighREV x5 | PSNR: 33.92 -> 35.42 | Improved |
| add Timesurface Dynamic Warping on top of RTEA (ablation) | TSANet (Case 2) · HighREV x5 | PSNR: 35.42 -> 36.84 | Improved |
| use timesurface instead of event-voxel features to guide warping (ablation) | TSANet · HighREV x5 | PSNR: 36.35 -> 36.84 | Improved |
| use EGGF fusion instead of concatenation (ablation) | TSANet · HighREV x5 | PSNR: 36.31 -> 36.84 | Improved |
| use EGGF fusion instead of element-wise addition (ablation) | TSANet · HighREV x5 | PSNR: 36.33 -> 36.84 | Improved |
| use EGGF fusion instead of cross-attention (ablation) | TSANet · HighREV x5 | PSNR: 36.79 -> 36.84 | Improved |
| time-specialized event-image alignment vs best prior event-based method | TSANet · GoPro x5 | PSNR: 27.76 -> 28.40 | 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.
- EvEnhancer — EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025) · better on 8 of 8 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
- CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring (ECCV 2024 · similarity 0.91)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.91)
- Motion Aware Event Representation-driven Image Deblurring (ECCV 2024 · similarity 0.91)
- Event-based Motion Deblurring with Unpaired Data (CVPR 2026 · similarity 0.90)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.89)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · 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.
