Existing style transfer methods have achieved great success in artwork generation by transferring artistic styles onto everyday photographs while keeping their contents unchanged. Despite this success, these methods have one inherent limitation: they cannot produce newly created image contents, lacking creativity and flexibility. On the other hand, generative adversarial networks (GANs) can synthesise images with new content, whereas cannot specify the artistic style of these images. The authors consider combining style transfer with convolutional GANs to generate more creative and diverse artworks. Instead of simply concatenating these two networks: the first for synthesising new content and the second for transferring artistic styles, which is inefficient and inconvenient, they design an end-to-end network called ArtistGAN to perform these two operations at the same time and achieve visually better results. Moreover, to generate images of higher quality, they propose the bi-discriminator GAN containing a pixel discriminator and a feature discriminator that constrain the generated image from pixel level and feature level, respectively. They conduct extensive experiments and comparisons to evaluate their methods quantitatively and qualitatively. The experimental results verify the effectiveness of their methods.

中文翻译：

---

利用对抗性网络生成创意多样的艺术品

现有的样式转移方法通过将艺术样式转移到日常照片上，同时保持其内容不变，在艺术品生成方面取得了巨大的成功。尽管取得了成功，但是这些方法具有一个固有的局限性：它们无法产生新创建的图像内容，缺乏创造力和灵活性。另一方面，生成对抗网络（GAN）可以合成具有新内容的图像，而不能指定这些图像的艺术风格。作者考虑将样式转换与卷积GAN结合使用，以生成更具创意和多样性的艺术品。除了简单地将这两个网络连接起来之外：第一个网络用于合成新内容，第二个网络用于传递艺术风格，这既效率低下又不方便，他们设计了一个名为ArtistGAN的端到端网络，以同时执行这两项操作，并在视觉上获得更好的效果。此外，为了生成更高质量的图像，他们提出了包含像素鉴别器和特征鉴别器的双鉴别器GAN，其分别从像素级别和特征级别约束生成的图像。他们进行了广泛的实验和比较，以定量和定性地评估他们的方法。实验结果证明了该方法的有效性。他们进行了广泛的实验和比较，以定量和定性地评估他们的方法。实验结果证明了该方法的有效性。他们进行了广泛的实验和比较，以定量和定性地评估他们的方法。实验结果证明了该方法的有效性。