Raindrop images generator#
Our experiments show the effectiveness of our approach, which outperforms the state of the art methods quantitatively and qualitatively.įig.1 The architecture of our proposed attentive GAN.The generator consists of an attentive-recurrent network and a contextual autoen- coder with skip connections. This injection of visual attention to both generative and discriminative networks is the main contribution of this paper.
Hence, by injecting this information, the generative network will pay more attention to the raindrop regions and the surrounding structures, and the discriminative network will be able to assess the local consistency of the restored regions. During the training, our visual attention learns about raindrop regions and their surroundings. Our main idea is to inject visual attention into both the generative and discriminative networks. To resolve the problem, we apply an attentive generative network using adversarial training. Second, the information about the background scene of the occluded regions is completely lost for most part. The problem is intractable, since first the regions occluded by raindrops are not given. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one.
Tan Wenhan Yang Jiajun Su Jiaying Liu adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably.
0 kommentar(er)
