ControlLight：迈向可控、一致且可泛化的低光增强

摘要

现有基于深度学习的低光照增强方法通常使用有限的数据集和单一的增强目标进行训练，这限制了它们在真实场景中的泛化能力和可控性。为克服这些局限，我们提出ControlLight——一种可控、一致且可泛化的低光照增强框架。我们首先构建了一个包含连续光照强度监督的大规模真实退化图像数据集。为确保在不同控制强度下输出结果的一致性，我们引入了一种对齐感知加权流匹配损失，该损失能在连续增强强度下保持图像结构。ControlLight允许用户通过灵活控制增强强度，在保持视觉一致性与真实性的同时，将真实场景的低光照退化图像编辑至满意的增强效果。大量实验表明，ControlLight在低光照增强任务上达到了现有方法的最优性能，并展现出强大的连续可控性和对真实场景的泛化能力。

English

Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weighted flow matching loss that preserves image structure across continuous enhancement strengths. ControlLight allows users to edit real-world degraded low-light images toward satisfactory enhancement results by flexibly controlling the strength while preserving visual consistency and realism. Extensive experiments show that ControlLight achieves state-of-the-art performance against existing low-light enhancement approaches while demonstrating strong continuous controllability and generalization to real-world scenarios.