Existing weak supervised low-light image enhancement methods lack enough effectiveness and generalization in practical applications. We suppose this is because of the absence of explicit supervision and the inherent gap between real-world low-light domain and the training low-light domain. For example, low-light datasets are well-designed, but real-world night scenes are plagued with sophisticated interference such as noise, artifacts, and extreme lighting conditions. In this paper, we develop Diffusion-based domain calibration to realize more robust and effective weak supervised Low-Light Enhancement, called DiffLLE. Since the diffusion model performs impressive denoising capability and has been trained on massive clean images, we adopt it to bridge the gap between the real low-light domain and training degradation domain, while providing efficient priors of real-world content for weak supervised models. Specifically, we adopt a naive weak supervised enhancement algorithm to realize preliminary restoration and design two zero-shot plug-and-play modules based on diffusion model to improve generalization and effectiveness. The Diffusion-guided Degradation Calibration (DDC) module narrows the gap between real-world and training low-light degradation through diffusion-based domain calibration and a lightness enhancement curve, which makes the enhancement model perform robustly even in sophisticated wild degradation. Due to the limited enhancement effect of the weak supervised model, we further develop the Fine-grained Target domain Distillation (FTD) module to find a more visual-friendly solution space. It exploits the priors of the pre-trained diffusion model to generate pseudo-references, which shrinks the preliminary restored results from a coarse normal-light domain to a finer high-quality clean field, addressing the lack of strong explicit supervision for weak supervised methods. Benefiting from these, our approach even outperforms some supervised methods by using only a simple weak supervised baseline. Extensive experiments demonstrate the superior effectiveness of the proposed DiffLLE, especially in real-world dark scenes.

现有的弱监督低照度图像增强方法在实际应用中缺乏足够的有效性和泛化性。我们假设这是因为缺乏明确的监督，以及真实世界的低光域和训练的低光域之间的固有差距。例如，低光数据集设计精良，但现实世界的夜景受到复杂干扰的困扰，例如噪点、伪影和极端照明条件。在本文中，我们开发了基于 Diffusion 的域校准，以实现更稳健和有效的弱监督 L ow-Light E增强，称为 DiffLLE。由于扩散模型具有令人印象深刻的去噪能力，并且已经在大量干净的图像上进行了训练，我们采用它来弥合真实的低光域和训练退化域之间的差距，同时为弱监督模型提供真实世界内容的有效先验。具体来说，我们采用一种朴素的弱监督增强算法来实现初步恢复，并基于扩散模型设计了两个零镜头的即插即用模块，以提高泛化和有效性。扩散引导降解校准 （DDC） 模块通过基于扩散的域校准和亮度增强曲线缩小了真实世界和训练低光降解之间的差距，这使得增强模型即使在复杂的野生降解中也能稳健地执行。由于弱监督模型的增强效果有限，我们进一步开发了 Fine-grained Target domain Distillation （FTD） 模块，以寻找一个更直观友好的解决方案空间。 它利用预训练扩散模型的先验来生成伪参考，将初步恢复的结果从粗略的法线光域缩小到更精细的高质量干净领域，解决了弱监督方法缺乏强显式监督的问题。受益于这些，我们的方法甚至仅使用简单的弱监督基线优于一些监督方法。广泛的实验证明了所提出的 DiffLLE 的卓越有效性，尤其是在现实世界的黑暗场景中。