Image generation from a single image using generative adversarial networks is quite interesting due to the realism of generated images. However, recent approaches need improvement for such realistic and diverse image generation, when the global context of the image is important such as in face, animal, and architectural image generation. This is mainly due to the use of fewer convolutional layers for mainly capturing the patch statistics and, thereby, not being able to capture global statistics very well. We solve this problem by using attention blocks at selected scales and feeding a random Gaussian blurred image to the discriminator for training. Our results are visually better than the state-of-the-art particularly in generating images that require global context. The diversity of our image generation, measured using the average standard deviation of pixels, is also better.
翻译:利用基因对抗网络从单一图像中生成图像非常有趣,因为生成图像的现实性。 但是,当图像的全球背景很重要,例如面部、动物和建筑图像生成时,最近的方法需要改进,以便产生现实和多样的图像。这主要是因为使用较少的卷变层主要捕捉补补丁统计数据,从而无法很好地捕捉全球统计数据。我们通过在选定尺度上使用关注区块和向培训歧视者输入随机的高斯模糊图像来解决这个问题。我们的结果比在生成需要全球背景的图像方面最先进的图像要好。用像素平均标准偏差来衡量的图像生成多样性也更好。