无需参考图，一键修复暗光图像的噪点与光照不均问题
Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
- 基于物理成像原理和Retinex理论，用分块图像对训练无监督模型
- 通过DCT频域分解与隐式引导表征，分离出复杂退化成分
- 适合处理真实场景暗光图像，可解释性强，开源代码已发布
真实世界的低光照图像常面临局部过曝、亮度不足、噪声和光照不均等多重退化。监督方法易在特定场景过拟合，而无监督方法因缺乏参考图像，难以建模复杂退化。为此，我们提出一种可解释的零参考联合去噪与低光增强框架，适用于真实场景。方法基于不同光照与噪声水平的配对子图像构建训练策略，结合物理成像原理与Retinex理论。同时，在sRGB空间中利用离散余弦变换（DCT）进行频域分解，并引入隐式引导的混合表征策略，有效分离复杂的复合退化。骨干网络设计采用受隐式退化表征机制引导的视网膜分解网络。大量实验表明，该方法显著优于现有方法。代码将公开于https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025。
原文摘要 · Abstract (English)
Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though better at generalization, struggle to model these degradations due to the lack of reference images. To address this issue, we propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios. Our method derives a training strategy based on paired sub-images with varying illumination and noise levels, grounded in physical imaging principles and retinex theory. Additionally, we leverage the Discrete Cosine Transform (DCT) to perform frequency domain decomposition in the sRGB space, and introduce an implicit-guided hybrid representation strategy that effectively separates intricate compounded degradations. In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms. Extensive experiments demonstrate the superiority of our method. Code will be available at https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025.
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。