ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement 事件

ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement arXiv:2605.25569v1 Announce Type: new Abstract: 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 enhancemen