Research map / Video / Video segmentation and tracking
Towards Real-world Event-guided Low-light Video Enhancement and Deblurring
Taewoo Kim, Jaeseok Jeong, Hoonhee Cho, Yuhwan Jeong, Kuk-Jin Yoon
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 ED-TFA module to baseline (ablation) | event-guided low-light deblurring network · RELED | PSNR: 29.59 -> 30.78 | Improved |
| add ED-TFA to a network that already has SFCM-FE (ablation) | event-guided network · RELED | PSNR: 30.40 -> 31.30 | Improved |
| add SFCM-FE module to baseline (ablation) | event-guided network · RELED | PSNR: 29.59 -> 30.40 | Improved |
| add SFCM-FE to a network with ED-TFA (ablation) | event-guided network · RELED | PSNR: 30.78 -> 31.30 | Improved |
| add channel attention blocks (CABs) or spatial attention alone in SFCM-FE (ablation) | SFCM-FE · RELED | PSNR: 30.78 -> 30.81 | No clear effect |
| add low-pass-filter modulation branch to SFCM-FE (ablation) | SFCM-FE · RELED | PSNR: 30.79 -> 31.22 | Improved |
| add CAB blocks on top of LPF branch (ablation) | SFCM-FE · RELED | PSNR: 31.22 -> 31.30 | Improved |
| replace SFCM-FE with EFNet or REFID cross-modal fusion (ablation) | event-guided network · RELED | PSNR: 31.3 -> 30.55 (EFNet), 31.3 -> 30.86 (REFID) | Hurt |
| compare proposed method with event-guided baselines | Ours vs REFID · RELED | PSNR: 30.10 -> 31.30 | Improved |
Closest papers by meaning
- Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring (ICCV 2025 · similarity 0.96)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.92)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.91)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.89)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.88)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.88)
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.
