Smoke removal has been a challenging problem which refers to the process of retrieving clear images from the smoky ones. It has an extensive demand while the performances of existing image desmoking methods have limitations owing to the homogeneous medium based model, hand-crafted features, and insufficient datasets. Unlike the existing desmoking methods using an atmospheric scattering model, the proposed method utilizes a general deblurring model. Inspired by Generative Adversarial Network (GAN), we propose an end-to-end attentive DesmokeGAN which implements the visual attention into the generative network to effectively learn the smoke features and their surroundings. The architecture of critic network is identical to PatchGAN by adding multi-component loss function to the image patch. Due to the scarce of various and quality smoke datasets, a graphics rendering engine is used to synthesize the smoky images. The quantitative and qualitative results show that the designed framework performs better than the recent state-of-the-art desmoking approaches on both synthetic and real images in indoor and outdoor scenes, especially for the thick smoky images.

除烟一直是一个具有挑战性的问题，它是指从烟熏图像中获取清晰图像的过程。由于基于均质介质的模型，手工制作的功能和不足的数据集，其具有广泛的需求，而现有图像除烟方法的性能受到限制。与现有的使用大气散射模型的除烟方法不同，所提出的方法利用了一般的去模糊模型。受生成对抗网络（GAN）的启发，我们提出了一种端到端细心的DesmokeGAN，该组件将视觉注意力引入生成网络中，以有效地学习烟雾特征及其周围环境。评论器网络的体系结构与PatchGAN相同，只是在图像补丁中添加了多分量损失功能。由于缺乏各种高质量的烟雾数据集，图形渲染引擎用于合成烟熏图像。定量和定性结果表明，所设计的框架在室内和室外场景的合成和真实图像上，尤其是对于浓烟图像，都比最近的最先进的除烟方法表现更好。