Abstract
Event cameras, with their high dynamic range, show great promise for Low-light Image Enhancement (LLIE). Existing works primarily focus on designing effective modal fusion strategies. However, a key challenge is the dual degradation from intrinsic background activity (BA) noise in events and low signal-to-noise ratio (SNR) in images, which causes severe noise coupling during modal fusion, creating a critical performance bottleneck. We therefore posit that precise event denoising is the prerequisite to unlocking the full potential of event-based fusion. To this end, we propose BiEvLight, a hierarchical and task-aware framework that collaboratively optimizes enhancement and denoising by exploiting their intrinsic interdependence. Specifically, BiEvLight exploits the strong gradient correlation between images and events to build a gradient-guided event denoising prior that alleviates insufficient denoising in heavily noisy regions. Moreover, instead of treating event denoising as a static pre-processing stage-which inevitably incurs a trade-off between over- and under-denoising and cannot adapt to the requirements of a specific enhancement objective-we recast it as a bilevel optimization problem constrained by the enhancement task. Through cross-task interaction, the upper-level denoising problem learns event representations tailored to the lower-level enhancement objective, thereby substantially improving overall enhancement quality. Extensive experiments on the Real-world noise Dataset SDE demonstrate that our method significantly outperforms state-of-the-art (SOTA) approaches, with average improvements of 1.30dB in PSNR, 2.03dB in PSNR* and 0.047 in SSIM, respectively. The code will be publicly available at this https URL.
Abstract (translated)
事件相机因其高动态范围，在低光图像增强（LLIE）方面展现出巨大潜力。现有研究主要集中在设计有效的模态融合策略上，然而一个关键挑战是事件中存在的固有背景活动（BA）噪声和图像中的低信噪比（SNR），这导致在模态融合过程中产生严重的噪声耦合现象，形成性能瓶颈的关键问题。因此，我们认为精确的事件去噪是解锁基于事件融合潜力的前提条件。为此，我们提出了BiEvLight，这是一个分层且任务感知的框架，通过利用其内在相关性来协同优化图像增强和去噪过程。 具体来说，BiEvLight 利用图像与事件之间的强梯度关联构建了一个引导式事件去噪先验模型，从而缓解了在高噪声区域中因去噪不足而产生的问题。此外，我们没有将事件去噪视为一个静态预处理阶段——这不可避免地会导致过度去噪和欠去噪之间的权衡，并且无法适应特定增强目标的需求——而是将其重新构造成一个受增强任务约束的双层优化问题。通过跨任务交互，上层去噪问题学习到了针对下层增强目标所需的事件表示形式，从而大幅提高了整体增强质量。 在真实噪声数据集SDE上的广泛实验表明，我们的方法显著优于现有最先进的（SOTA）方法，在PSNR、PSNR*和SSIM方面分别平均提升了1.30dB、2.03dB 和 0.047。代码将公开发布在此链接：[https://github.com/your-repo-url](https://github.com/your-repo-url)（请确保替换为实际的GitHub存储库URL）。
URL
https://arxiv.org/abs/2603.04975
