Research map / Video / Video segmentation and tracking
Separation for Better Integration: Disentangling Edge and Motion in Event-based Deblurring
Yufei Zhu, Hao Chen, Yongjian Deng, Wei You
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 plain cross-attention event fusion (ablation) | two-stage U-Net baseline · EVRB | PSNR: 28.65 -> 30.71 | Improved |
| add edge-aware sharpening module (ablation) | baseline · EVRB | PSNR: 28.65 -> 31.13 | Improved |
| add edge-aware sharpening instead of plain event attention (ablation) | baseline with events · EVRB | PSNR: 30.71 -> 31.13 | Improved |
| add deformable conv with offsets from image features (ablation) | baseline · EVRB | SSIM: 28.65 -> 28.80 | No clear effect |
| add deformable conv with event-feature offsets (ablation) | baseline · EVRB | PSNR: 28.65 -> 30.51 | Improved |
| add motion-driven deformable conv using motion cues (ablation) | baseline · EVRB | PSNR: 28.65 -> 31.63 | Improved |
| use motion cues instead of full event features for DCN offsets (ablation) | baseline with event DCN · EVRB | PSNR: 30.51 -> 31.63 | Improved |
| combine edge-aware sharpening with motion-driven deblurring (ablation) | B+MotionDCN · EVRB | PSNR: 31.63 -> 32.05 | Improved |
| combine motion-driven deblurring with edge-aware sharpening (ablation) | B+EdgeAtt · EVRB | PSNR: 31.13 -> 32.05 | Improved |
| compare single-frame model with multi-frame CMTA-5 | Ours · GoPro | PSNR: 36.55 -> 36.70 | Improved |
| compare single-frame model with CMTA-7 | Ours · GoPro | PSNR: 36.78 -> 36.70 | Hurt |
| compare with FEVD multi-frame on REVD | Ours · REVD | PSNR: 32.99 -> 32.14 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- CMTA-7 — CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring (ECCV 2024) · better on 1 of 4 shared results
- REDNet — RED-Net: A Recurrent Encoder–Decoder Network for Video-Based Face Alignment (IJCV 2018) · 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
- Event-based Motion Deblurring with Unpaired Data (CVPR 2026 · similarity 0.94)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.92)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.91)
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring (AAAI 2025 · similarity 0.90)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.90)
- Diffusion-based Event Generation for High-Quality Image Deblurring (CVPR 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.
