CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhong, Mingchen, Lu, Xin, Li, Dong, Xu, Senyan, Jiang, Ruixuan, Fu, Xueyang, Yin, Baocai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912883733954560
author Zhong, Mingchen
Lu, Xin
Li, Dong
Xu, Senyan
Jiang, Ruixuan
Fu, Xueyang
Yin, Baocai
author_facet Zhong, Mingchen
Lu, Xin
Li, Dong
Xu, Senyan
Jiang, Ruixuan
Fu, Xueyang
Yin, Baocai
contents 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 complex-valued signal processing in both spatial and frequency domains, facilitating deep fusion through spatial structures and system-level characteristics. By leveraging the holistic representation capability of complex-valued neural networks, CompEvent achieves full-process spatiotemporal fusion, maximizes complementary learning between modalities, and significantly strengthens low-light video deblurring capability. Extensive experiments demonstrate that CompEvent outperforms SOTA methods in addressing this challenging task.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring
Zhong, Mingchen
Lu, Xin
Li, Dong
Xu, Senyan
Jiang, Ruixuan
Fu, Xueyang
Yin, Baocai
Computer Vision and Pattern Recognition
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 complex-valued signal processing in both spatial and frequency domains, facilitating deep fusion through spatial structures and system-level characteristics. By leveraging the holistic representation capability of complex-valued neural networks, CompEvent achieves full-process spatiotemporal fusion, maximizes complementary learning between modalities, and significantly strengthens low-light video deblurring capability. Extensive experiments demonstrate that CompEvent outperforms SOTA methods in addressing this challenging task.
title CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.14469