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

arXiv: https://arxiv.org/abs/2603.04975 · HTML: https://mlsanity.com/paper/2603.04975/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Gradient-based Hyperparameter Optimization through Reversible Learning](https://mlsanity.com/paper/1502.03492/) (2015)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Truncated Back-propagation for Bilevel Optimization](https://mlsanity.com/paper/1810.10667/) (2018)
- [Implicit Neural Representation for Cooperative Low-light Image Enhancement](https://mlsanity.com/paper/2303.11722/) (2023)
- [Event Enhanced High-Quality Image Recovery](https://mlsanity.com/paper/2007.08336/) (2020)
- [FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information](https://mlsanity.com/paper/2308.03033/) (2023)
- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach](https://mlsanity.com/paper/2404.00834/) (2024)
- [Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras](https://mlsanity.com/paper/2003.08282/) (2020)
- [Seeing Motion at Nighttime with an Event Camera](https://mlsanity.com/paper/2404.11884/) (2024)
- [Event-based Camera Pose Tracking using a Generative Event Model](https://mlsanity.com/paper/1510.01972/) (2015)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Empowering Low-Light Image Enhancer through Customized Learnable Priors](https://mlsanity.com/paper/2309.01958/) (2023)
- [URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration](https://mlsanity.com/paper/2505.23068/) (2025)
- [Low-Light Image Enhancement using Event-Based Illumination Estimation](https://mlsanity.com/paper/2504.09379/) (2025)

## Built on by (most cited first, 1 of 1)

- [EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement](https://mlsanity.com/paper/2606.29430/) (2026)

## Abstract (arXiv)

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.