MR. Illuminate：基于扩散先验的零样本低光照图像增强
MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior
利用预训练扩散模型的自注意力特征做局部结构/颜色精修，并用 AdaIN 调制全局光照与色彩，无需任何优化或退化假设即可零样本增强——这为把扩散模型的内部特征当作免训练先验用于底层复原任务提供了可复用范式。
原文依据 the first deep learning-based solution for LLIE that requires no optimization and no degradation assumption
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论低光照图像增强（LLIE）关注的核心维度是色彩恒常性——即对同一场景在不同光照与噪声条件下的输入产生一致的输出——以及跨多样数据集的泛化能力。现有方法无论是有监督、无监督还是零样本，都依赖辅助损失函数与经验选取的超参数，在评测所用数据集上效果良好，但泛化能力往往有限。为克服这些限制，我们提出 MR. Illuminate（读作“Mister Illuminate”），这是首个无需优化、也无需退化假设的基于深度学习的 LLIE 方案。“MR.”强调我们的调制—精修（Modulate-Refine）设计：全局光照与色彩通过自适应实例归一化（AdaIN）进行调制，而局部结构与色彩则借助预训练扩散模型内部的自注意力特征进行精修，与先前方法采取了截然不同的思路。大量定量评估表明，我们的方法在标准 LLIE 基准上超越了 SOTA 方法，定性结果则显示出更优的色彩保真度。此外，在不对方框架做任何修改的情况下，我们的方法在自动白平衡（AWB）任务上取得了有竞争力的结果，凸显了其强大的泛化能力。
英文原文摘要 1322 字符
The primary axes of interest in low-light image enhancement (LLIE) are color constancy--ensuring consistent outputs across inputs of the same scene under varying illumination and noise--and generalization across diverse datasets. Existing methods, whether supervised, unsupervised, or zero-shot, rely on auxiliary loss functions and empirically selected hyperparameters, which yield strong results on the datasets used for evaluation but often exhibit limited generalization. To overcome these constraints, we propose MR. Illuminate (pronounced "Mister Illuminate"), the first deep learning-based solution for LLIE that requires no optimization and no degradation assumption. "MR." emphasizes our Modulate-Refine design: global illuminance and color are modulated via Adaptive Instance Normalization (AdaIN), while local structure and color are refined through self-attention features within a pre-trained diffusion model, taking a unique approach from prior methods. Extensive quantitative evaluations show that our approach surpasses SOTA methods on standard LLIE benchmarks, while qualitative results demonstrate improved color fidelity. Moreover, without any modification to our framework, our method achieves competitive results on the auto white balance (AWB) task, underscoring its strong generalization capability.