Research map / Video / Video segmentation and tracking
Learning Event-Based Motion Deblurring
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the recurrent event-assisted deblurring method rather than the strongest listed baseline | GoPro single-image deblurring · GoPro | PSNR: 31.50 -> 31.79 | Helped |
| Use the recurrent event-assisted deblurring method rather than the strongest listed baseline | GoPro video reconstruction · GoPro | PSNR: 28.49 -> 29.67 | Helped |
| Use the recurrent event-assisted deblurring method rather than the strongest listed baseline | Blur-DVS single-image deblurring · Blur-DVS | PSNR: 26.08 -> 26.48 | Helped |
| Use the recurrent event-assisted deblurring method rather than the strongest listed baseline | Blur-DVS video reconstruction · Blur-DVS | PSNR: 24.10 -> 25.33 | Helped |
| Add event input to blurred-image appearance (ablation) | Blur-DVS deblurring · Appearance-only model | PSNR: 16.50 -> 23.39 | Helped |
| Add blurred-image appearance to events and motion compensation (ablation) | Blur-DVS deblurring · Events + MC model | PSNR: 16.38 -> 24.71 | Helped |
| Add motion compensation (ablation) | Blur-DVS deblurring · Appearance + events | PSNR: 23.39 -> 24.71 | Helped |
| Add directional event filtering boundary guidance (ablation) | Blur-DVS deblurring · Appearance + events + MC | PSNR: 24.71 -> 25.33 | Helped |
| Add directional event filtering boundary guidance (ablation) | Blur-DVS deblurring · Full method versus without guidance | SSIM: 0.786 -> 0.827 | Helped |
| Use boundary guidance alone, without event features in each sequential step (ablation) | Blur-DVS deblurring · Guidance-only variant | SSIM: 0.786 -> 0.816 | Helped |
| Replace DEF with additional convolution layers in the process encoder (ablation) | Blur-DVS deblurring · Extra-parameter variant | SSIM: 0.786 -> 0.788 | No clear effect |
Closest papers by meaning
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.91)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.90)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.90)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.88)
- Diffusion-based Event Generation for High-Quality Image Deblurring (CVPR 2025 · similarity 0.87)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.87)
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.