# Bilevel Generative Learning for Low-Light Vision

arXiv: https://arxiv.org/abs/2308.03381 · HTML: https://mlsanity.com/paper/2308.03381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (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)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [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)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization](https://mlsanity.com/paper/2112.12376/) (2021)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion](https://mlsanity.com/paper/2305.15862/) (2023)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [Abandoning the Bayer-Filter to See in the Dark](https://mlsanity.com/paper/2203.04042/) (2022)
- [An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection](https://mlsanity.com/paper/2305.09999/) (2023)
- [Recurrent Exposure Generation for Low-Light Face Detection](https://mlsanity.com/paper/2007.10963/) (2020)
- [Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond](https://mlsanity.com/paper/2305.06720/) (2023)
- [Towards Fast and Light-Weight Restoration of Dark Images](https://mlsanity.com/paper/2011.14133/) (2020)
- [Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision](https://mlsanity.com/paper/2112.04719/) (2021)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Searching a Compact Architecture for Robust Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12236/) (2023)
- [Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application](https://mlsanity.com/paper/2205.10146/) (2022)

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

- [On the Stability and Generalization of First-order Bilevel Minimax Optimization](https://mlsanity.com/paper/2604.20115/) (2026)

## Abstract (arXiv)

Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.