BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement

TL;DR

BiEvLight introduces a hierarchical, task-aware framework that jointly optimizes event denoising and low-light image enhancement, significantly improving performance by leveraging their intrinsic interdependence and a novel bilevel optimization approach.

Contribution

It proposes a novel bilevel optimization framework for joint event denoising and low-light image enhancement, addressing noise coupling and improving overall enhancement quality.

Findings

Outperforms state-of-the-art methods with 1.30dB PSNR improvement

Achieves 2.03dB higher PSNR* and 0.047 SSIM on real-world noise dataset

Demonstrates the effectiveness of task-aware, joint optimization in event-based low-light enhancement

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 https://github.com/iijjlk/BiEvlight.