Low-light image enhancement based on optimized depth neural network
In order to solve the problem of low quality image caused by global climate,a low-illumination image enhancement model based on optimized depth neural network is proposed in this paper.The model utilizes the least squares generation antagonism network to learn the mapping between low-light and normal-light images,and introduces the attention mechanism in U-Net to enhance the dark regions in low-light images.It is proved that the model can produce satisfactory visual effect and image quality from subjective and objective angles through experiments.
NETL
NSTL
万方数据
