Single Image Dehazing Network Based on Serial Feature Attention

Images captured under hazy weather conditions often show significant degradation, limiting their applications in military reconnaissance, traffic monitoring, and other fields. To obtain clear and haze free images, the paper proposes a dehazing network based on serial feature attention. The network adaptively captures the inter-dependency between features from channel and spatial perspectives, respectively, learns the weights of features, and uses long and short jump connections to make the network more focused on the important information of haze concentration to improve the network dehazing performance. Extensive experiments are conducted on synthetic and real scene datasets, and the results show that the proposed method recovers haze image with natural colors and high image quality.