Research map / Video / Video segmentation and tracking
Event-Based Fusion for Motion Deblurring with Cross-Modal Attention
Lei Sun, Christos Sakaridis, Jingyun Liang, Qi Jiang, Kailun Yang, Peng Sun, Yaozu Ye, Kaiwei Wang, Luc Van Gool
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 SCER event input via early fusion to 2-stage image-only network (ablation) | 2-stage network · GoPro | PSNR (dB): improves PSNR by 1.53 dB and SSIM by 0.6% | Improved |
| use multi-level middle fusion instead of early fusion with simple fusion (ablation) | EFNet · GoPro | PSNR (dB): ~1 dB in PSNR and 0.7% in SSIM | Improved |
| use EICA cross-modal attention instead of multiplication or addition fusion (ablation) | EFNet · GoPro | PSNR (dB): 0.6 dB or more in PSNR and 0.4% in SSIM | Improved |
| add EMGC connection between stages (ablation) | EFNet · GoPro | PSNR (dB): 35.31 -> 35.46 | Improved |
| add second stage to image-only network (ablation) | image-only network · GoPro | PSNR (dB): 29.06 -> 32.15 | Improved |
| add second stage to EFNet with events (ablation) | EFNet · GoPro | PSNR (dB): 34.90 -> 35.46 | Improved |
| use SCER instead of SBT event representation (ablation) | EFNet · GoPro | PSNR (dB): 35.12 -> 35.46 | Improved |
| use simple Stack event accumulation instead of no events (ablation) | 2-stage network · GoPro | PSNR (dB): 32.15 -> 31.90 | Hurt |
| use EICA instead of concatenation fusion (ablation) | EFNet · GoPro | PSNR (dB): 34.80 -> 35.46 | Improved |
| add SCER events to HINet input (ablation) | HINet · GoPro | PSNR (dB): 32.71 -> 33.69 | Improved |
| add SCER events to SRN input (ablation) | SRN · GoPro | PSNR (dB): 30.26 -> 31.02 | Improved |
| add SCER events to HINet input | HINet · REBlur | PSNR (dB): 35.58 -> 37.68 | Improved |
Closest papers by meaning
- Motion Aware Event Representation-driven Image Deblurring (ECCV 2024 · similarity 0.93)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.93)
- Diffusion-based Event Generation for High-Quality Image Deblurring (CVPR 2025 · similarity 0.91)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.91)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.91)
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring (AAAI 2025 · similarity 0.90)
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.
