Self-supervised Image Enhancement Network: Training with Low Light Images Only
This addresses image quality improvement for low light photography, offering a simple and fast solution that is incremental in its approach.
The paper tackles low light image enhancement by proposing a self-supervised deep learning method based on a maximum entropy Retinex model, achieving state-of-the-art processing speed and effect with minute-level training using only low light images.
This paper proposes a self-supervised low light image enhancement method based on deep learning. Inspired by information entropy theory and Retinex model, we proposed a maximum entropy based Retinex model. With this model, a very simple network can separate the illumination and reflectance, and the network can be trained with low light images only. We introduce a constraint that the maximum channel of the reflectance conforms to the maximum channel of the low light image and its entropy should be largest in our model to achieve self-supervised learning. Our model is very simple and does not rely on any well-designed data set (even one low light image can complete the training). The network only needs minute-level training to achieve image enhancement. It can be proved through experiments that the proposed method has reached the state-of-the-art in terms of processing speed and effect.