Attention-generative adversarial networks for simulating rain field

The synthesis of rain fields is essential in multiple research fields and applications, including Single-image Derain. However, there is a lack of research on simulated rain fields, and the existing rain field generation models struggle to capture complex spatial distributions and generate truly random rain fields. To address this, the authors propose a generative adversarial networks-based rain field generation network, which consists of a generator, a discriminator, and a feature extraction block that can produce realistic and complex rain fields. The authors' experiments demonstrate that this method achieves an average Frechet Inception Distance score of 0.035, and user studies indicate that the generated rain distribution looks naturally. This article proposes a generative adversarial networks-based rain field generation network to address the lack of research on simulated rain fields and the struggles of the existing models in generating truly random and complex rain fields. The proposed network includes a generator, a discriminator, and an encoder that produces realistic rain fields, achieving an average Frechet Inception Distance score of 0.035, and passing user studies for natural-looking rain distribution. image