Research map / Video / Video segmentation and tracking
CrossZoom: Simultaneous Motion Deblurring and Event Super-Resolving
Chi Zhang, Xiang Zhang, Mingyuan Lin, Cheng Li, Chu He, Wen Tao Yang, Gui-Song Xia, Lei Yu
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 multi-scale blur-event fusion (MBEF) (ablation) | CZ-Net · CRDR | PSNR: +1.19 dB PSNR, +0.0182 SSIM | Improved |
| add attention-based adaptive enhancement (AAE) (ablation) | CZ-Net · CRDR | PSNR: +0.59 dB PSNR, +0.0086 SSIM | Improved |
| add cross-interaction prediction (CIP) (ablation) | CZ-Net · CRDR | PSNR: +1.36 dB PSNR, +0.0196 SSIM | Improved |
| add ESR loss L_esr to deblurring loss (ablation) | CZ-Net · CRDR | PSNR: 25.43 -> 25.86 | Improved |
| add attention loss L_att to deblurring loss (ablation) | CZ-Net · CRDR | PSNR: 25.43 -> 26.05 | Improved |
| add L_att on top of L_md + L_esr (ablation) | CZ-Net · CRDR | PSNR: 25.86 -> 26.93 | Improved |
| add L_esr on top of L_md + L_att (ablation) | CZ-Net · CRDR | PSNR: 26.05 -> 26.93 | Improved |
| joint deblurring and event super-resolving instead of two-stage cascade | CZ-Net · GoPro single frame | PSNR: 8.3 dB PSNR gain, 0.158 SSIM gain | Improved |
| joint network instead of SRFBN for event super-resolving | CZ-Net · GoPro E2VID | SSIM: 0.3598 -> 0.3930 | Improved |
Closest papers by meaning
- Event-Based Fusion for Motion Deblurring with Cross-Modal Attention (ECCV 2022 · similarity 0.91)
- CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring (ECCV 2024 · similarity 0.90)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.89)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.89)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.88)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · 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.
