Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
It addresses image restoration for computer vision applications, but is incremental as it builds on existing GAN frameworks with attention mechanisms.
The paper tackles the problem of removing raindrops from single images, which degrade visibility, by proposing an attentive generative adversarial network that injects visual attention into both generative and discriminative networks, resulting in outperforming state-of-the-art methods quantitatively and qualitatively.
Raindrops adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one. The problem is intractable, since first the regions occluded by raindrops are not given. Second, the information about the background scene of the occluded regions is completely lost for most part. To resolve the problem, we apply an attentive generative network using adversarial training. Our main idea is to inject visual attention into both the generative and discriminative networks. During the training, our visual attention learns about raindrop regions and their surroundings. 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. This injection of visual attention to both generative and discriminative networks is the main contribution of this paper. Our experiments show the effectiveness of our approach, which outperforms the state of the art methods quantitatively and qualitatively.