# Bilevel Fast Scene Adaptation for Low-Light Image Enhancement

arXiv: https://arxiv.org/abs/2306.01343 · HTML: https://mlsanity.com/paper/2306.01343/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 68 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network](https://mlsanity.com/paper/2106.14501/) (2021)
- [Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation](https://mlsanity.com/paper/1910.13616/) (2019)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton](https://mlsanity.com/paper/2006.04045/) (2020)
- [Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset](https://mlsanity.com/paper/1908.00682/) (2019)
- [Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond](https://mlsanity.com/paper/2110.00455/) (2021)
- [A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization](https://mlsanity.com/paper/2106.07991/) (2021)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [Unsupervised Domain Adaptation for Nighttime Aerial Tracking](https://mlsanity.com/paper/2203.10541/) (2022)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [Fast Adaptation to Super-Resolution Networks via Meta-Learning](https://mlsanity.com/paper/2001.02905/) (2020)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)

## Built on by (most cited first, 22 of 22)

- [Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model](https://mlsanity.com/paper/2308.13164/) (2023)
- [LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models](https://mlsanity.com/paper/2407.08939/) (2024)
- [Empowering Low-Light Image Enhancer through Customized Learnable Priors](https://mlsanity.com/paper/2309.01958/) (2023)
- [Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion](https://mlsanity.com/paper/2309.01113/) (2023)
- [Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction](https://mlsanity.com/paper/2309.00872/) (2023)
- [FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder](https://mlsanity.com/paper/2404.17936/) (2024)
- [Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement](https://mlsanity.com/paper/2404.17400/) (2024)
- [Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution](https://mlsanity.com/paper/2411.12530/) (2024)
- [Harnessing Meta-Learning for Improving Full-Frame Video Stabilization](https://mlsanity.com/paper/2403.03662/) (2024)
- [Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction](https://mlsanity.com/paper/2309.01183/) (2023)
- [ASF-Net: Robust Video Deraining via Temporal Alignment and Online Adaptive Learning](https://mlsanity.com/paper/2309.00956/) (2023)
- [AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training](https://mlsanity.com/paper/2309.01106/) (2023)
- [Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation](https://mlsanity.com/paper/2309.03548/) (2023)
- [Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement](https://mlsanity.com/paper/2507.18064/) (2025)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Bilevel Generative Learning for Low-Light Vision](https://mlsanity.com/paper/2308.03381/) (2023)
- [Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework](https://mlsanity.com/paper/2309.01099/) (2023)
- [Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling](https://mlsanity.com/paper/2504.12204/) (2025)
- [From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration](https://mlsanity.com/paper/2505.22284/) (2025)
- [Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement](https://mlsanity.com/paper/2508.09009/) (2025)
- [BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement](https://mlsanity.com/paper/2603.04975/) (2026)
- [ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement](https://mlsanity.com/paper/2407.19708/) (2024)

## Abstract (arXiv)

Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before. The main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. To remedy this, we first explore relationships between diverse low-light scenes based on statistical analysis, i.e., the network parameters of the encoder trained in different data distributions are close. We introduce the bilevel paradigm to model the above latent correspondence from the perspective of hyperparameter optimization. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i.e., freezing the encoder in the adaptation and testing phases). Further, we define a reinforced bilevel learning framework to provide a meta-initialization for scene-specific decoder to further ameliorate visual quality. Moreover, to improve the practicability, we establish a Retinex-induced architecture with adaptive denoising and apply our built learning framework to acquire its parameters by using two training losses including supervised and unsupervised forms. Extensive experimental evaluations on multiple datasets verify our adaptability and competitive performance against existing state-of-the-art works. The code and datasets will be available at https://github.com/vis-opt-group/BL.