Gated Contiguous Memory U-Net for Single Image Dehazing

Single image dehazing is a challenging problem that aims to recover a high-quality haze-free image from a hazy image. In this paper, we propose an U-Net like deep network with contiguous memory residual blocks and gated fusion sub-network module to deal with the single image dehazing problem. The contiguous memory residual block is used to increase the flow of information by feature reusing and a gated fusion sub-network module is used to better combine the features of different levels. We evaluate our proposed method using two public image dehazing benchmarks. The experiments demonstrate that our network can achieve a state-of-the-art performance when compared with other popular methods.