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

TL;DR
CompEvent introduces a complex-valued neural network framework that holistically fuses event data and RGB frames to improve low-light video deblurring and enhancement, outperforming existing methods.
Contribution
The paper presents a novel complex neural network architecture with temporal alignment and space-frequency modules for full-process fusion of event and RGB data.
Findings
Outperforms state-of-the-art methods in low-light video deblurring
Achieves superior fusion of event and RGB modalities
Enhances low-light video restoration quality
Abstract
Low-light video deblurring poses significant challenges in applications like nighttime surveillance and autonomous driving due to dim lighting and long exposures. While event cameras offer potential solutions with superior low-light sensitivity and high temporal resolution, existing fusion methods typically employ staged strategies, limiting their effectiveness against combined low-light and motion blur degradations. To overcome this, we propose CompEvent, a complex neural network framework enabling holistic full-process fusion of event data and RGB frames for enhanced joint restoration. CompEvent features two core components: 1) Complex Temporal Alignment GRU, which utilizes complex-valued convolutions and processes video and event streams iteratively via GRU to achieve temporal alignment and continuous fusion; and 2) Complex Space-Frequency Learning module, which performs unified…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAdvanced Image Processing Techniques · Generative Adversarial Networks and Image Synthesis · Image and Video Quality Assessment
