提出一种快速低光图像增强方法，无需大量训练数据
RetinexGuI: Retinex-Guided Iterative Illumination Estimation Method for Low Light Images
- 基于Retinex理论分离光照与反射层，迭代优化光照分量
- 计算复杂度仅O(N)，在三个公开数据集上表现优异
- 适合实时应用，可与深度学习结合，开源可复现
近年来，由于对关键下游任务的重要性，低光图像增强（LLIE）受到越来越多关注。现有基于Retinex的方法和学习型方法虽表现出色，但计算复杂度高且依赖大规模训练数据，限制了其在实时场景中的应用。本文提出RetinexGuI，一种新颖有效的Retinex引导式低光图像增强框架。该方法首先将输入图像分解为光照与反射分量，并在保持反射分量不变的前提下，迭代优化光照分量。其简化公式具有$/mathcal{O}(N)$的计算复杂度，在三个公开数据集上均展现出出色的增强效果，表明其在大规模应用中具有巨大潜力。此外，该方法为理论分析及与深度学习融合提供了新方向。代码将在论文录用后公开于https://github.com/etuspars/RetinexGuI。
原文摘要 · Abstract (English)
In recent years, there has been a growing interest in low-light image enhancement (LLIE) due to its importance for critical downstream tasks. Current Retinex-based methods and learning-based approaches have shown significant LLIE performance. However, computational complexity and dependencies on large training datasets often limit their applicability in real-time applications. We introduce RetinexGuI, a novel and effective Retinex-guided LLIE framework to overcome these limitations. The proposed method first separates the input image into illumination and reflection layers, and iteratively refines the illumination while keeping the reflectance component unchanged. With its simplified formulation and computational complexity of $\mathcal{O}(N)$, our RetinexGuI demonstrates impressive enhancement performance across three public datasets, indicating strong potential for large-scale applications. Furthermore, it opens promising directions for theoretical analysis and integration with deep learning approaches. The source code will be made publicly available at https://github.com/etuspars/RetinexGuI once the paper is accepted.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。