Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
This work improves low-light image enhancement for computer vision applications by leveraging event cameras, providing both a novel method and a new dataset to advance the field.
The authors propose EIC-LIE, an event-illumination collaborative framework for low-light image enhancement that addresses noise sensitivity in event signals and global illumination. Their method achieves up to 1.24dB PSNR and 0.069 SSIM improvement over state-of-the-art on five datasets, and they release a new high-resolution real-world event-based LIE dataset.
Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking the essential global illumination in images and the inherent noise sensitivity of event signals in real-world scenarios. To address these issues, we propose EIC-LIE, an event-illumination collaborative LIE framework. Concretely, we first design an Event-Illumination Collaborative Interaction (EICI) module, which contains two key processes: forward gathering, which gathers HDR features across varying lighting conditions, and backward injection, which provides complementary content for illumination and event representations. Next, we introduce an Illumination-aware Event Filter (IAEF) that dynamically reduces event noise based on brightness statistics derived from images. Additionally, we build a beam-splitter-based hybrid imaging system to collect high-quality event-image pairs with temporal synchronization from dynamic scenes, providing the first high-resolution, real-world event-based LIE dataset. Extensive experiments show that our EIC-LIE outperforms state-of-the-art methods on five real-world and synthetic datasets, significantly surpassing previous methods with improvements of up to 1.24dB in PSNR and 0.069 in SSIM. The code and dataset are released at https://github.com/QUEAHREN/EIC-LIE.