提出可调控的低光增强框架，实现真实场景下的稳定一致效果。
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
- 构建含连续光照标注的大规模真实低光图像数据集
- 引入误对齐感知加权流匹配损失，保持不同增强强度下图像结构一致
- 支持灵活调节增强强度，适合真实复杂场景应用
现有基于深度学习的低光增强方法通常在有限数据集上训练，且仅针对单一增强目标，限制了其在真实场景中的泛化能力和可控性。为此，我们提出ControlLight，一种可调控、一致且具备强泛化能力的低光增强框架。首先，构建包含连续光照强度标注的大规模真实退化图像数据集；为确保不同控制强度下的输出一致性，引入误对齐感知加权流匹配损失，有效保留图像结构。ControlLight允许用户通过灵活调节增强强度，对真实低光图像进行可控优化，同时保持视觉一致性和真实性。大量实验表明，该方法在现有低光增强模型中达到领先性能，并展现出优异的连续可控性与真实场景泛化能力。
原文摘要 · Abstract (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.
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。