Research map / Video / Video segmentation and tracking
CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring
Mingchen Zhong, Xin Lu, Dong Li, Senyan Xu, Ruixuan Jiang, Xueyang Fu, Baocai Yin
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 |
|---|---|---|---|
| use complex convolution for RGB-event fusion instead of real-valued concatenation (ablation) | CompEvent · RELED | PSNR: 31.39 -> 32.51 | Improved |
| add CTA-GRU temporal alignment (vs no GRU) (ablation) | CompEvent · RELED | PSNR: 30.87 -> 32.51 | Improved |
| use CTA-GRU instead of cross-frame concatenation (ablation) | CompEvent · RELED | PSNR: 31.93 -> 32.51 | Improved |
| add frequency branch to CSFL (ablation) | CompEvent · RELED | PSNR: 31.76 -> 32.51 | Improved |
| use complex layer normalization (whitening) instead of separate real-valued normalization (ablation) | CompEvent · RELED | PSNR: 31.98 -> 32.51 | Improved |
| use complex layer normalization instead of joint normalization of concatenated parts (ablation) | CompEvent · RELED | PSNR: 31.55 -> 32.51 | Improved |
| use CompEvent instead of ELEDNet (staged event-RGB fusion) | joint low-light enhancement and deblurring · LOL-Blur | PSNR: 25.04 -> 28.73 | Improved |
| use CompEvent instead of ELEDNet | joint low-light enhancement and deblurring · RELED | PSNR: 31.30 -> 32.51 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EvLight++ — EvLight++: Low-Light Video Enhancement With an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More (TPAMI 2025) · 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 Fusion for Motion Deblurring with Cross-Modal Attention (ECCV 2022 · similarity 0.89)
- Towards Real-world Event-guided Low-light Video Enhancement and Deblurring (ECCV 2024 · similarity 0.87)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.87)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.86)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.86)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.85)
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.
