Research map / Video / Video segmentation and tracking
Motion Aware Event Representation-driven Image Deblurring
Zhijing Sun, Xueyang Fu, Longzhuo Huang, Aiping Liu, 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 |
|---|---|---|---|
| use deviation accumulation (DA) event representation instead of best alternative (SCER) (ablation) | event-based deblurring network · GoPro | PSNR: 35.81 -> 36.07 | Improved |
| use stack representation instead of DA (ablation) | event-based deblurring network · GoPro | PSNR: 36.07 -> 33.24 | Hurt |
| add recurrent motion extraction (RME) module instead of a conv block (ablation) | event-based deblurring network · GoPro | PSNR: 35.42 -> 36.07 | Improved |
| use FAF alignment-and-fusion instead of cross-modality attention (ablation) | event-based deblurring network · GoPro | PSNR: 35.75 -> 36.07 | Improved |
| use FAF instead of direct concatenation (ablation) | event-based deblurring network · GoPro | PSNR: 34.02 -> 36.07 | Improved |
| bi-directional alignment instead of aligning only one modality (ablation) | FAF module · GoPro | PSNR: 35.78 -> 36.07 | Improved |
| add DA event representation to image-only HINet | HINet · GoPro | PSNR: 32.71 -> 34.63 | Improved |
| add DA event representation to image-only UFPNet | UFPNet · GoPro | PSNR: 34.06 -> 35.22 | Improved |
Closest papers by meaning
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.92)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.91)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.90)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.90)
- Diffusion-based Event Generation for High-Quality Image Deblurring (CVPR 2025 · similarity 0.90)
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion 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.
