论文标题
通过在静态视频上学习跨框架的注意来增强低光视频
Low Light Video Enhancement by Learning on Static Videos with Cross-Frame Attention
论文作者
论文摘要
由于难以捕获弱光和地面真相视频对，因此对低光视频增强的深度学习方法的设计仍然是一个具有挑战性的问题。在动态场景或移动摄像机的背景下，这尤其困难，在无法捕获长时间的曝光地面真相。我们通过在静态视频上训练模型来解决这个问题，以便该模型可以推广到动态视频。采用此方法的现有方法逐帧运行，并且不利用相邻框架之间的关系。我们通过自我越界扩张的注意模块克服了这一限制，即使在训练和测试时间之间，即使框架之间的动态不同，也可以有效地学习使用相邻框架的信息。我们通过在多个数据集上的实验来验证我们的方法，并表明我们的方法仅在静态视频上接受培训时，我们的方法优于其他最先进的视频增强算法。
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or moving cameras where a long exposure ground truth cannot be captured. We approach this problem by training a model on static videos such that the model can generalize to dynamic videos. Existing methods adopting this approach operate frame by frame and do not exploit the relationships among neighbouring frames. We overcome this limitation through a selfcross dilated attention module that can effectively learn to use information from neighbouring frames even when dynamics between the frames are different during training and test times. We validate our approach through experiments on multiple datasets and show that our method outperforms other state-of-the-art video enhancement algorithms when trained only on static videos.
